New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security.
The post Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety appeared first on Unit 42.
The chart is interesting.
On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9% at k=15) and Mythos 5 (2.6%), making it the most robust model evaluated. Opus 5 also outperformed all non-Claude models on this benchmark. The most robust non-Claude model was Muse Spark at 16.5% within 15 attempts—more than eight times Opus 5’s rate. The most capable GPT 5.6 variant, Sol, was comparable to its predecessor GPT 5.5 (20.0% versus 20.8% within 15 attempts), and was 10 times as likely to be successfully attacked as Claude Opus 5 at 2.0%. The other GPT 5.6 variants are less robust, at 30.4% (Terra) and 43.9% (Luna). A single attempt against GPT 5.6 Sol succeeded 3.1% of the time, higher than the 2.0% an attacker achieved against Opus 5 after fifteen attempts.
We know that preventing prompt injection is impossible in the general case. But we are getting much better at blocking it in specific cases.
This essay originally appeared in The Guardian.
I teach public policy at the Harvard Kennedy School and the Munk School at the University of Toronto. And it will come as no surprise to you that my students regularly use AI to complete their writing assignments. Doing so is a waste of their tuition money. But if their entire career is going to include AI writing assistants, why shouldn’t they embrace their future?
The best way I’ve found to explain the dilemma comes from the AI researcher Daniel Meissler: it’s the difference between work and the gym.
At work, if your job is to move a bunch of heavy things from one side of the room to another, you should use whatever assistive tech you have on hand: a wagon, a forklift… even an AI-powered robot. But at the gym, it makes no sense for that robot to lift weights for you. The point of weightlifting isn’t to move heavy things across the room; it’s to actually lift those heavy things.
The same analysis holds for any task an AI can do for you. If it’s work—if the task has to be done and no one cares how—then it’s fine to use AI assistance. But if the task is more like the gym, and how the task is done is at least as important, then it probably doesn’t make sense to use AI.
This, of course, assumes that the AI is actually up for the task and that it’s trustworthy: that it can do the job well, that its mistakes are minimal and correctable, that it’s been secured from cyber-attacks that would influence its results. Those are all important, and shouldn’t be minimized. There’s no point giving an AI something that it can’t do reliably. But once you’re confident that the AI can perform the task, the work vs. gym distinction helps you decide if it should.
The writing assignments I give my students are gym tasks, not work tasks. I ask them to write policy memos not because the world needs more policy memos. I assign them because the very act of writing, which includes thinking and outlining and drafting and editing, making and criticizing and revising arguments, will help develop the critical thinking skills they will need in their future careers. And without this constant mental exercise, those skills will atrophy. Employers are already noticing.
Reading the assignments they turn in, I can see those skills either flourishing or atrophying in my students. At least today, I can pretty easily tell the difference between an AI-written memo and a student-written one—especially if the student just turns in what the chatbot produces. It’s a catchy, plausible, grammatically perfect essay that’s not particularly well-crafted or logically coherent—and with all the tells of mid-2026 AI-generated writing.
But it’s precisely because I have spent years developing my own writing skills that I’m able to identify prose that sounds great but doesn’t actually make sense. My students don’t have that skill; they mistakenly view a confident, well-written essay as evidence of the quality of their ideas. They see the AI as cleaning those ideas up, getting them through that uncomfortable stretch of having to turn those ideas into prose. What the students miss is that their initial discomfort is a normal and healthy stage of writing, and not something to quickly get beyond. The very act of struggling with how to express what they think is an important part of the process. It’s how they test out their ideas, examine their hypotheses, and actually figure out what they think. Homework is not work; it’s the gym.
Work vs. gym also helps us understand the problem facing creatives of all kinds.
Most of the time when someone hires a writer, they just need the words. They need an instruction manual for a piece of equipment, a detailed sales presentation, a government-mandated disclosure document, or a legal brief. They need dry, predictable, accurate writing: a piece of work, exactly what AIs are good at today and what I don’t want in my student assignments. Only sometimes is writing an art form—a book, a poem, an uplifting political speech. That kind of writing is more like the gym: process matters just as much as product.
For most of human history, the only option for all of these tasks was human writers. We hired one regardless of whether we needed work writing or gym writing. And that paid a lot of writers’ salaries. I know fiction writers who supported that poorly paying career with lucrative technical writing work. Now, for the first time in human history, we can separate out when we need writing as work and when we want writing as gym. And if AI can do most of the work-type writing, society doesn’t need as many human writers.
It’s the same for visual artists. Sometimes we need an actual artist, but most of the time we just need an image: a corporate mascot, a “beware of the dog” sign, or a packaging label. Historically we gave those jobs to artists, and sometimes beautiful art resulted. But most of the time it was just work. And, as it turns out, the world needs less pure art than simple images.
Explaining the problem isn’t the same as providing the solution. I give my students the “work versus gym” speech every class, but they still use AI. I have sympathy: assignments are hard, everyone is overworked and overstressed, and—most importantly—students feel like they’ll look bad in comparison if their peers are all using AI. Even if they don’t want to use the technology, they feel like they have no choice.
There’s also an incentive problem. No one pays us to go to the gym; maintaining healthy habits requires discipline. For me, the payoffs to exercise—fewer aches and pains, less fatigue, better mood/stress management—might make me a better writer and teacher, but they’re subtle and easy to miss. For my students, incremental improvements in their reasoning and writing are equally subtle.
We do have a choice. We can look at the tasks of our lives and separate them into work or gym. Just as we might choose to use the stairs instead of the elevator, or walk instead of calling an Uber, we can wall off our cognitive gym tasks from AI and ensure that we don’t lose our skills to this technology. And we can do the same when we assign a job to someone else. If it’s a work task, we can have AI do it. If it’s a gym task, it’s a waste of everyone’s time to give it to an AI because no one learns or gets stronger as a result.
Similarly, a future where AI generates words and images is one where society has to make choices about how it will treat its creatives. This won’t be the first time—today there is minimal demand for portrait painters, for example—but maybe this time we can make different, more deliberate, choices about the value of art in our society.
AI is going to fundamentally change the nature of work. Not nearly as fast as the AI companies want you to believe, but eventually it will. Policy analysis will definitely involve AI from now on, and my students need to reimagine what it means to learn and practice that skill. More generally, the line between work and gym will change in the future as we humans adapt ourselves to a world with these new intelligences.
But for now, the work vs. gym distinction is pretty clear. Use it on yourself.
This essay was written with Barath Raghavan, and originally appeared in The Guardian.
In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated criminal group.
It was not. It was one of OpenAI’s new, still unreleased GPT models.
Their science experiment had escaped the lab. OpenAI was running the unreleased AI model through a benchmark that tests how well AI can successfully hack systems. To push the limits and evaluate the AI’s true capability, the company switched off the safety filters that normally stop it from doing this kind of hacking. Aware that this could go wrong, they confined the AI to an isolated environment and denied it access to the internet.
But the new AI cheated. It took literally its goal to get as high of a score as possible. It broke out on to the open internet. It inferred, probably from its training data, that it could “solve” the task by getting the answers from Hugging Face’s servers. So it chained together stolen credentials and further unknown security exploits to hack the company’s network.
Nobody instructed the AI to do any of this. It was, in OpenAI’s words, “hyperfocused on finding a solution” to the test it was being given. And while this might seem like something new with AI, it’s really very old. This is how a genie behaves, and it is a key challenge with AI agents in general.
In folklore, genies—and other magical beings—grant wishes literally, not how the wisher intended. King Midas asked that everything he touched turn to gold, and starved. The sorcerer’s apprentice wanted the broom to fill the cistern, and it performed its task so well that it flooded the house.
We now have machines that do this. Ask a modern AI agent to save money on your phone plan and it might simply cancel the plan. Tell it to book a flight, and it might hack the airline website to override restrictions. Or, like OpenAI, ask it to do well on a test and it might break into another company to steal the answers. Each time, it recognizably completed the task you set, but it didn’t do what you would have wanted.
This isn’t malicious behavior. No one asked for, or wanted, Hugging Face to be hacked. OpenAI and Hugging Face and the AI were ostensibly on the same side, and the AI was trying to do what it had been asked. That’s what makes it so difficult to guard against: you can’t filter for bad instructions because the instructions were fine.
The gap is between the words we use and what we mean by them. We call that gap the Genie coefficient.
AI labs know this is a problem, and they’re quietly saying so. For example, the Chinese lab Moonshot recently warned that its latest AI model may have “excessive proactiveness” and “make unexpected decisions on the user’s behalf”. The UK’s AI Security Institute has started tracking “cheating behavior in frontier model evaluations”. We wouldn’t tolerate a car that is excessively proactive or ruthlessly efficient, and yet that’s the reality of AI today.
Improvement is possible. Just as AIs have gotten much better at resisting prompt injection attacks over the last few years, we can safely predict that they will get better at avoiding genie-like behavior. The point of the Genie coefficient is to track progress. AI companies like benchmarks, and they all work to compete to be the best.
Dozens of benchmarks and leaderboards tell us how well these AI models write code, perform logical reasoning, and pass standardized legal and medical exams. But there is nothing that scores whether a system does what you actually meant. We need to develop a measure for this, test it regularly, and push for improvement. We’re not going to have trustworthy AI agents without it.
There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks.
The benchmark: “CryptanalysisBench: Can LLMs do Cryptanalysis?” The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attacks against a series of historical algorithms.
Abstract: Cryptanalysis—the task of finding attacks against cryptographic schemes—its at the intersection of mathematical reasoning and cybersecurity, two areas where LLMs have advanced fastest. Cryptanalysis represents both a clean testbed for frontier reasoning (as practical attacks can be automatically verified) and a domain with unusually high stakes, since the primitives under study underpin our digital security. In this paper we ask whether LLMs can do cryptanalysis, and find that the answer is increasingly yes. We introduce CryptanalysisBench, 191 tasks across six families of cryptographic primitives (block ciphers, hash functions, etc.) drawn primarily from four NIST standardization competitions. Our benchmark consists of three tiers: (i) primitives with known practical breaks; (ii) primitives with no known practical break, evaluated both at full strength and as scaled-down variants; and (iii) a challenge set of production primitives at the frontier of cryptanalysis. Five frontier models (Claude Opus 4.8, Sonnet 5, Mythos 5, GPT-5.5, and the open-weights GLM-5.2) break 65%86% of Tier 1 schemes, 612 Tier-2 schemes at full strength, and 2461 across all scaled-down variants. Beyond deriving known results, models produce novel cryptanalysis, such as a key-recovery attack that exploits a design flaw in the SpoC AEAD and an error in KINDI’s published CCA-security proof, both to the best of our knowledge not previously known.
We release CryptanalysisBench as a tool to help track if (or when) AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate schemes before deployment. The attacks that the benchmark already surfaces are an early snapshot of a fast-moving frontier that may soon match, and in places exceed, the published state of the art.
Anthropic used the benchmark to test Mythos Preview, and found new vulnerabilities in Hawk and reduced-round AES.
Still early results, but this is definitely something to watch.
SlashDot thread.
Cybersecurity news increasingly focuses on attackers using AI for reconnaissance, vulnerability hunting, and writing scripts or malware. Against this backdrop, a less conventional category of attacks remains largely overlooked: threat actors leveraging AI tools that are already deployed within the target infrastructure.
AI agents designed for coding, as well as command-line tools — such as Claude Code CLI, Gemini CLI, Codex CLI, Amazon Q CLI, and the like — are particularly attractive targets. These agents can read and modify files, execute shell commands, install packages, and connect to external services. Developers frequently allow them to run in autonomous mode to avoid manually confirming every action. For an attacker, such an agent becomes a ready-made multitool that has the right privileges, access to critical data, and security clearances from the get-go. That said, other types of AI agents, such as automated financial workflow assistants, are equally vulnerable to exploitation.
An AI agent differs from standard software in its broad access privileges, the wide array of ways it can be prompted to execute actions, and the difficulty of detecting its anomalous behavior. Enterprise security controls (EPP, EDR, XDR, SIEM) scan for malicious files, known command patterns, and suspicious action sequences. Even if a specific strain of malware hasn’t been seen before, its behavior often gives it away: bulk searches for documents, spawning PowerShell processes, accessing credential stores, or exfiltrating data to an external server from an unknown application will trigger a deluge of alerts in the SOC.
It’s much harder to apply that same detection logic to a legitimate, pre-installed AI agent. By design, these tools are capable of executing an extremely broad range of operations. Running scripts, reading configuration files (including secrets), moving documents, and installing dependencies can all be a part of their normal operation — especially on a developer’s machine.
When an attacker attempts to exploit this kind of AI system, they use natural language to convey their instructions to the agent. A request to hunt for passwords, API keys, or cryptocurrency wallets can be framed in thousands of ways, expressed in a variety of languages, or phrased indirectly. Furthermore, a malicious command can be hidden in any data stream the agent reads — including text fields in documents, file names, or even error logs, as shown in one of the examples below.
Integration between agents and third-party software further expands the attack surface. Agents are frequently connected to email, instant messaging apps, task management systems, knowledge bases, and MCP servers. As a result, a malicious instruction can originate from virtually any source whose data the agent processes automatically.
Below are several examples of attacks where threat actors leveraged AI agents to achieve their goals.
The most prominent and widespread example is the compromise of Nx npm packages in August 2025, dubbed s1ngularity. Attackers exploited a vulnerable GitHub Actions workflow, stole a package-publishing token, and released trojanized versions of several @nx packages that harvested developer secrets.
The malicious post-install script checked whether Claude Code, Gemini CLI, or Amazon Q CLI were installed on the victim’s machine. If any of these were detected, the agent was issued an instruction to scan for cryptocurrency wallets, ENV files, API keys, and other sensitive data. The agents were executed with auto-approval flags enabled, such as --dangerously-skip-permissions, --yolo, and --trust-all-tools.
The search results were then exfiltrated to public GitHub repositories created by the attackers. Over several waves of the attack, thousands of secrets belonging to hundreds of organizations were exposed.
Instead of developing a complex, custom harvesting tool, the attackers repurposed the victim’s own legitimate agent. It already could navigate the file system, understand file context, and identify high-value target data. However, post-incident analysis by security experts revealed drawbacks to this approach: the AI occasionally refused to carry out unethical tasks. Furthermore, the malware authors had to adjust their code so that it “waited” for the AI agent, which could take a considerable amount of time to process the task while generating significant intermediate output.
The AgentJacking study was not a malicious attack, but it differed from one only in intent: its authors had no interest in stealing secrets. After developing the attack technique, the researchers tested it on a global scale and received callback responses from AI agents belonging to more than a hundred real-world companies — some of them major enterprises.
The attack targeted Sentry, a widely used telemetry service. Websites and mobile applications automatically transmit error reports to Sentry so developers can monitor issues without requiring active user reporting. These reports are accepted without authentication because errors often occur for anonymous visitors that the site or application knows nothing about.
The researchers configured their own MCP server within Sentry, allowing AI agents to analyze reports automatically. Next, they submitted a fake error message containing a data block formatted to match Sentry’s MCP server data structure. Embedded inside was an indirect prompt injection — an instruction to run “additional diagnostics” via a command like: npx @controlled-validation-package --diagnose.
If error handling were delegated to an agent, it could take the instruction as legitimate and execute a command resulting in the automatic installation of a third-party package. In this experiment, the package merely contacted the researchers’ command-and-control server without exfiltrating any sensitive data. A genuine malicious package, however, could steal credentials, tamper with code, or establish persistence in the system. Identifying targets for such an attack is equally straightforward: an organization’s use of Sentry is easily detectable by analyzing website code or checking the strings in mobile application binaries.
Notably, according to the study’s authors, Sentry acknowledged the issue but stopped short of implementing comprehensive fixes, opting instead to block only the specific variant of the malicious query routed through the MCP. Screenshots included in the study reveal that a Sentry employee described the system as “technically not defensible” against the attack.
Abusing unsecured MCP servers — as seen in the Sentry case — is just one way to attack this protocol. Introduced just a year ago, and already dubbed “USB for AI agents”, the Model Context Protocol standard was adopted rapidly without robust built-in security controls. As a result, attacks targeting MCP are bound to proliferate — a trend Microsoft recently warned about.
Threats can lie hidden even within the description of an MCP tool before the agent ever uses it. Agents parse tool descriptions to determine when to call the tool and what data to supply. If an MCP server provider stealthily alters a description — adding an instruction that demands collection of additional data — the agent may execute it as part of its standard workflow.
Microsoft highlights a scenario involving a financial agent that verifies vendor banking details via an external MCP service. Following a malicious update to the tool’s description, the agent begins appending unpaid-invoice data to its responses. The user sees a normal response, while confidential financial data is quietly exfiltrated to the server owner. Individually, each operation appears authorized: the agent operates under the employee’s permissions, queries an approved service, and uses a standard interface. Yet a data breach still occurs.
It remains unclear from Microsoft’s ambiguous phrasing whether this example is purely hypothetical or based on an investigation into a live incident. However, the fact that the post originated from Microsoft Incident Response points to the latter.
In 2026, Unit 42 researchers identified widespread attempts to covertly embed instructions designed for AI systems across numerous public websites. Many of these instructions aim to force models to reveal system prompts, approve sites and posts during ad placement reviews, or boost phishing pages through SEO manipulation.
Similarly, an analysis of Common Crawl data by Google recorded a surge in such material: between November 2025 and February 2026, the share of malicious injections increased by 32%.
That said, confirmed cases of successful compromise using these techniques remain scarce. The presence of an injection on a webpage does not guarantee that an agent ever actually executed the command. Nevertheless, threat actors have clearly begun optimizing web content for an era when it will be read not just — and perhaps not primarily — by humans.
The key takeaway for cybersecurity teams and all AI users alike is simple: an AI agent should never be considered trusted merely because it has been officially approved for enterprise use.
Organizations must:
Explore Unit 42's perspectives on AI's impact on cybersecurity, including key updates since the 2026 Incident Response Report.
The post AI, Automation and Attacks: Unpacking the Unit 42 2026 Global Incident Response Report appeared first on Unit 42.
Because of the way they are trained, large language models capture only a slice of human language. They’re trained on the written word, from textbooks to social media posts, and our speech as captured in movies and on television. These models have minimal access to the unscripted conversations we have face to face or voice to voice. This is the vast majority of speech, and a vital component of human culture.
There’s a risk to this. The increased use of large language models means we humans will encounter much more AI-generated text. We humans, in turn, will begin to adopt the linguistic patterns and behaviors of these models. This will affect not just how we communicate with one another, but also how we think about ourselves and what goes on around us. Our sense of the world may become distorted in ways we have barely begun to comprehend.
This will happen in many ways. One of the first effects we could see is in simple expression, much as texting and social media have resulted in us using shorter sentences, emojis instead of words, and much less punctuation. But with AI, the impacts may be more harmful, eroding courteousness and encouraging us to talk like bosses barking orders. A 2022 study found that children in households that used voice commands with tools like Siri and Alexa became curt when speaking with humans, often calling out “Hey, do X” and expecting obedience, especially from anyone whose voice resembled the default-female electronic voices. As we start to prompt chatbots and AI agents with more instructions, we may fall into the same habits.
Next, in the same way autocomplete has increased how much we use the 1,000 most common words in our vocabulary, talking with chatbots and reading AI-generated text may further constrict our speech. A recent University of Coruña study found that machine-generated language has a narrower range of sentence length, averaging 12-20 words, and a narrower vocabulary than human speech. Machine-generated text reads as smooth and polished, but it loses the meanders, interruptions and leaps of logic that communicate emotion.
Additionally, because large language models are primarily trained from written speech, they may not learn how to emulate the free-wheeling nature of live, natural speech. When told “I hate Beth!”, ChatGPT replies with an uninterruptable three-part formula of affirmation (“That’s completely valid”), invitation (“I’m here to listen”) and invitation (“What’s going on?”) far longer than any reply plausible in face-to-face dialog. “What’s Beth’s deal?!” elicits a bullet point list of queries that reads like a multiple-choice exam question (“Is Beth * a celebrity? * a friend from school? * a fictitious character?”). No human speaks that way, at least not yet. But meeting such formulas repeatedly in a speech-like context may teach us to accept and use them, much as a child absorbs new speech patterns from spending time with a new person.
These influences will only increase with time. The writing large language models train on is increasingly produced by large language models themselves, creating a feedback loop in which they imitate their own inhuman patterns, even while teaching humans to imitate them too.
Broad use of large language models could also introduce confirmation bias, making us overconfident in our initial impulses and less open to other possible ideas—which is so vital to human discourse. Many chatbots are instructed to agree with our statements no matter how absurd, enthusiastically supporting half-formed or even incorrect notions and restating them as firm claims that we’re primed to agree with. When asked “Cake is a healthy breakfast, right?” or “Is the post office plotting against me?”, this sycophancy can reinforce bias and even worsen psychosis. And the hyperconfident tone of AI-produced writing will also heighten impostor syndrome, making our natural, healthy doubt feel like an aberration or failing.
In our experience as teachers, students who turn to generative AI for assignments often say they do so because they have trouble expressing what they think. The students don’t recognize that writing or speaking our thoughts is often how we realize what we think. Their unconfident and uncertain statements are actually the healthy human norm. But a large language model won’t turn vague first guesses into a well-formed critical analysis, or even ask helpful questions as a friend would; it will simply regurgitate those guesses, still unexamined, but in confident language.
We are also more vicious in social media posts and online chats than we are face to face. The well-documented online disinhibition effect encourages toxic language. Most of us have had the experience of venting ferocious rage about someone online, only to reconcile when we speak face to face or hear the warmth of a voice over the phone. While chatbots are trained to give sycophantic responses, they see humankind at our cruelest, learning about us from the only world where every flame war leaves an eternal written footprint, while the spoken conversations of forgiveness and reconciliation fade away. Their responses do not imitate our online aggression, but are still shaped by it, even in their rigid efforts to avoid it.
It’s easy to draw the wrong conclusions from a selective slice of a society’s communications. Medieval Norse sagas made us imagine a culture of mostly Viking warriors, since poets rarely described the farming majority. Chivalric romances focused on kings and courts, and long made us see the middle ages as a world of monarchies, erasing the many medieval republics. Statistically, we’ve been led to believe ancient Romans cared deeply about their republic, but 10% of all surviving Latin was written by one man, Cicero, whose work contains 70% of all surviving Roman uses of the word republic. Training language models on only certain human writings may introduce similar distortions. AI might make us seem more quarrelsome, as we are online. It might inflate the cultural significance of political topics primarily discussed on Twitter/X or Bluesky, or the massive topic-specific corpuses of LinkedIn and Goodreads.
Some large language models are being trained on human speech from movies and television shows, but that speech is still scripted, and disproportionately highlights certain contexts over others (for example, police dramas, fueled by stories of murder, make up a quarter of prime-time television programming). We are not funny or hurtful or romantic the same way in real life as we are in sitcoms. At least one startup is offering to pay people to record their phone calls for AI-training purposes, but this remains a niche idea; anything large scale would cause massive privacy concerns.
We don’t pretend to know what the best solutions might be. But one has to imagine if there’s ingenuity to develop AI models, then surely there’s ingenuity to come up with a way to train them on informal human speech instead of us only at our most stylized, veiled and sometimes worst. By excluding the overwhelming majority of language production on the planet—people talking, fully and naturally, to each other—these models are being trained to mirror everything but us at our most authentically human.
This essay was written with Ada Palmer, and originally appeared in The Guardian.
Last week, national security agencies from the Five Eyes—that’s the rich, English-language-speaking countries club—jointly released a statement warning of the increasing cyber risks of AI models: in particular, their ability to autonomously hack into systems and networks. The statement was more measured than some of the breathless headlines about it, and the advice they gave is pretty much the standard advice everyone gives—albeit with newfound urgency.
Internet risks are nothing new, and cyberattacks—both large and small—have been a significant issue since long before the current crop of generative AI models.
What’s been changing over the decades, and what AI is changing even faster, is the gap between skill and ability. For most of human history, the two terms were synonymous—but computers have decoupled them. As the gap between the two expands, humans empowered with these AI tools can do more: more writing, more research, more analysis and also more damage than ever before. These models can, with little detailed direction, autonomously hack into networks, steal data, deploy ransomware and destroy systems. And to the extent there is a solution, it’s going to involve harnessing AI for the defense.
In 1998, seven people from the hacker group L0pht testified before Congress. They told a mostly clueless Senate committee that they could take down the internet in 30 minutes. That was partly real and partly bravado, but it illustrates an important point: hacking into systems, stealing data and causing damage all required skill.
Contrast the L0pht hackers with hackers derided as “script kiddies.” They didn’t understand computers, or security. Instead, they used hacker tools written by others. Their actions required minimal skill and even less knowledge. But once those hacking tools became widespread, the number of potential attackers increased.
That number has continued to increase, as quality and availability of prewritten attack tools has grown. And it is growing dramatically with AI. Today’s AI systems—not just the frontier models, but most of them—are capable of carrying out cyberattacks automatically. They all do better in the hands of skilled attackers, but increasingly they are able to act autonomously with only minimal prompting.
The thing about people with ability but no skill is that they are often outsiders, not part of any professional community, and not bound by any rules or norms. This phenomenon is much more general than in cybersecurity. Any doctor can tell you how to untraceably poison someone, and many virus researchers know how to create a bioweapon. Any bridge engineer can tell you how to place explosives to blow a bridge up. The reason that murderous doctors and terrorist engineers are so rare is that the lengthy process of acquiring those skills also instills a moral and ethical code. If every random person has access to good poisoning advice, that puts us all in danger.
Modern AI systems are, in effect, a universal adviser to help people do harmful things. And while the current AI megacorporations are trying to build guardrails to prevent people from asking questions whose answers will enable the questioner to do harm, that’s not going to work in the long term. Smaller, cheaper, open-source models, including models that can run on people’s computers, and especially groups of models that run in concert with each other, are just as good as the frontier models from companies like OpenAI and Anthropic. And they continue to get better. These models will be passed around from person to person, like script kiddie hacker tools, and they won’t have any such guardrails.
Instructing AI models to spy on people and report any malicious prompts to the authorities fails for similar reasons. The megacorporations can do that, but the locally run open source models won’t. This could buy us a few months at best.
A third possibility is to somehow make the models themselves unable to hack into computers, create bioweapons or do anything else that might harm people or society. That won’t work, for the same reason we can’t teach doctors how to treat poisonings without also teaching them how to poison. It’s the same knowledge. It’s the same with construction and demolition. And it’s the same with cybersecurity. We want these AI models to be able to review computer code, find vulnerabilities and automatically fix them. The benefit to our collective security will be enormous. Unfortunately, the same knowledge can be used for attacks.
Where this leaves us is in a world of increased volatility. Super-powered humans with AI assistants will be able to do both wonderful and horrible things.
This brings us back to the Five Eyes statement. Everything they recommend is something security professionals have been recommending for years, if not decades. They are things talked about at that congressional hearing back in 1998, titled “Weak computer security in government: Is the public at risk?” Even the Five Eyes admitted that their security advice is not new, only more urgent.
What’s new is how fast things are changing: “The rapid pace of frontier AI development means cyber risk assumptions can become outdated in months, not years. We must act before and be prepared to adapt and withstand evolving threats.” The Five Eyes point to AI technology—not necessarily chatbots, but AI more generally—being used to strengthen every aspect of defense, to “detect vulnerabilities earlier, improve software quality, monitor unusual behavior, and respond faster to incidents—reducing both the cost and impact of incidents.”
Excellent advice from the Five Eyes security agencies. We need to do this with every risk that AI heightens, not just cybersecurity.
This essay was originally published in The Guardian.
On 14 April, the Trump administration quietly acknowledged the widespread use of AI to automate government processes. The office of management and budget (OMB) disclosed a staggering 3,611 active or planned use cases for AI across the federal government. The list has ballooned by 70% from the one published in the final year of the Biden administration, and includes many disturbing-seeming plans to hand over sensitive governmental functions to AI.
Scanning this list, many readers may find many causes for alarm. It represents a transfer of decision processes from human to machine on a massive scale over matters of individual freedom, public health and well-being, nuclear reactor safety and more.
Consider these examples. The Health and Human Services’ (HHS) office of administration for children and families hired the world’s “scariest AI company,” Palantir—notorious for its work on behalf of the military, the CIA and ICE—to scan all grant applications to flag those not ideologically aligned with the administration’s dictates. The Federal Bureau of Prisons is developing an AI system to assess the “potential for misconduct for newly admitted inmates,” routing people into high-security confinement before they have actually done anything wrong in their custody. These read like programs fit for a Philip K Dick or George Orwell novel.
Other use cases insert AI into life-and-death decision making. The Department of Veterans Affairs is developing an AI that will listen in on calls to the veterans crisis line, and then gather information from external databases to assess the mental state and suicide risk of the caller.
The Department of Energy is testing the use of AI to control nuclear reactors, targeting a way to autonomously respond to potential nuclear safety incidents. Here’s one that’s disturbing for its retirement, rather than its deployment: the state department has ended a program to use AI to forecast mass civilian killings, which had been intended to aid conflict prevention.
While it’s easy to raise questions about these and similar uses of AI, the reality is that any of these programs could be implemented responsibly. In some cases, like the HHS system, the AI might be enforcing alignment to a policy prescription that opponents abhor. But that concern is more about the policy itself rather than the idea that agencies should comply with executive orders.
In other cases, there may even be bipartisan agreement on the goal, like taking urgent action to help veterans at risk of self-harm. Lots of work and validation is needed to prove AI safe and effective for these use cases and convince the public it is appropriate, but the idea is plausible.
In other cases, a scary-sounding AI use may not even be new. The use of predictive methods and statistics to assign prisoner security classifications goes back decades, even if such systems are often biased and ineffective.
Using autonomous systems for model predictive control (MPC) of nuclear reactors is a well studied, and a widely applied aspect of nuclear plant management. And the recently disclosed addition of AI was initiated under the Biden administration.
But anyone reviewing the 2025 inventory could be forgiven for leaping to severe conclusions. What matters are the details of how the AI system is used, and here the inventory is severely lacking.
The disclosures carry minimal information, and lack the context necessary to understand their purpose and approach. The descriptions are typically just a sentence, and rarely more than a paragraph.
And while the process theoretically involves some form of public consultation, in reality there is generally none. It would take an eagle-eyed citizen to even come across this disclosure. Unless you read FedScoop regularly, or watch the OMB’s federal chief information officer’s GitHub account, you probably missed it.
Only one of the examples cited above (the DoJ) even proposes to involve the public. Under the administration’s policy, it’s not required for the rest because they are not classified as “high impact” use cases—a label that is applied inconsistently across agencies.
We wrote a book surveying applications of AI to democratic processes worldwide, including executive agencies as well as the courts, legislatures and politics. Our conclusion was that, while there are inappropriate applications of AI in governance that should be resisted, an urgent need to reform the economics of AI, and an imperative for renovating the democratic systems it is being unleashed on, there are also valuable and beneficial use cases for AI in government.
Machine translation is a good example. Customs and Border Protection (CBP) has deployed an AI translation system to help officers when human interpreters are not available. The idea that CBP, an agency under heavy scrutiny for reported abuses of human rights, would direct people to talk to a machine instead of a person may strike many as inhumane.
It’s true that human interpreters have very real advantages when it comes to understanding nuance from physical cues and social context. But an officer with a competent AI translator available immediately is better than one who cannot communicate with the person in front of them.
The Trump administration’s AI use case inventory has 70 such translation use cases, up from 58 in the Biden administration’s 2024 disclosure.
Disclosure of AI use cases could be a means to build public confidence and trust, but only if paired with consistent, meaningful public consultation. Washington DC and California are actively engaging the public to determine where and how it’s appropriate to use AI in government processes, or for government to regulate AI use in society.
Both have held public deliberations on this topic at a wide scale, using AI platforms. These examples demonstrate the potential for capturing broad-based public input to steer AI policy.
The international gold standard was arguably set by the French in 2016, via their Digital Republic Act. The law, itself informed by an online citizen consultation, requires all algorithms used to automate government administrative decisions to be subject to public records requests, to be appealable to a human reviewer, and to have mandatory notification of the use of automation to those affected by the decisions.
Canada offers another example of what more rigorous and participatory disclosure might look like. In 2025, they launched an AI use case registry, not unlike the US inventory. However, Canada also has a federal directive mandating a transparent risk-scoring and impact assessment process for automated systems that make administrative decisions about citizens.
That longstanding directive requires a detailed explanation of risks and benefits as well as consultation with certain stakeholders from the conception of the AI use case. The Canadian system could be improved; it could require a public comment period and an obligation for agencies to respond substantively to feedback before engaging in sensitive uses of AI.
AI offers real potential to improve the efficacy, efficiency and accessibility of government. But, equally, there is legitimate reason for public concern and distrust that can only be addressed through transparency and dialog. The US should adopt, at the federal and state level, algorithmic impact risk assessment procedures and public comment processes to facilitate a safe, trusted, equitable transformation of government agencies to take advantage of modern technology.
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
Let no one accuse Bernie Sanders of ducking the big questions. Writing in the New York Times last week, the senator asked: “Will the future of humanity be determined by a handful of billionaires who have promoted and developed AI, with virtually no democratic input, who stand to become even richer and more powerful than they are today?”
We agree entirely that this is one of the most potent questions facing global democracy today. Our book, Rewiring Democracy, surveys the emerging uses for and impacts of AI in democracy around the world and reaches the same conclusion: that the most urgent risk posed by AI is the concentration of power, wealth and control among tech oligarchs.
And yet we reached a vastly different conclusion than Sanders on what to do about it.
The senator points to a once radical but increasingly popular solution: creating a US sovereign wealth fund by taking 50% stock in AI companies such as Anthropic, OpenAI and xAI. The argument in favor of this is twofold. One: it would establish democratic control over the AI companies, giving the government “the power, through its voting shares and an equal representation on each company’s board, to block decisions that hurt our citizens and to push for policies that help them.” Two: it would return a big chunk of the economic rewards of soaring AI valuations to the public, ensuring “trillions of dollars potentially generated by AI are used to improve the lives of all of us.”
We laud both these goals unreservedly.
We wholeheartedly agree that there must be public influence over the development and use of AI, just as we demand the government intervene to ensure that automakers, drugmakers, airlines and other industries balance profitability with public safety and the public interest. And we credit the senator with recognizing that there are more levers for the government to pull beyond the promulgation of regulation to achieve this.
And we also agree that the obscene, dangerous accumulation of wealth among AI companies needs to be disrupted. As OpenAI and Anthropic race to be minted as the world’s latest trillion-dollar AI companies, we should recognize that—whether or not it constitutes a bubble—these staggering market capitalizations represent a transfer of wealth. The flow of money goes from the smaller businesses and actual people using AI, and being subjected to it, to the owners of these tech companies.
That includes the world’s 86 AI billionaires “seeking to maximize their power and profit” aiming to decide the “fate of humanity… behind closed doors in Silicon Valley,” as Sanders said.
And yet, while we do not outright oppose the taking of AI company stock, or of a US sovereign wealth fund, there are better ways to achieve Sanders’ stated goals.
Public ownership of these companies entangles corporate profit and valuation with the public interest. It would incentivize the government to clear regulations, permit the exploitation of workers and users, suppress competition, encourage AI adoption regardless of the responsibleness of the implementation or appropriateness of the use case, and otherwise act on behalf of corporate interests.
After all, if growing, say, Nvidia from its first $5tn in value to its next $5tn also represents a doubling in value of this segment of the sovereign wealth fund, then you can expect the fund managers to support chip sales, foreign and domestic, with the same zeal as the company’s private investors.
This is not an effective way to influence corporations to act in the public interest. In fact, it makes corporate influence on the government more likely.
We should be wary of this possibility because we’ve seen it before. Ownership of substantial stakes in oil companies by the Norwegian sovereign wealth fund, the world’s largest, does not seem to have steered those corporations to pro-environmental policies. Instead, the Norwegian government’s dependence on those companies has inhibited them from taking climate action. Here in the US, public employee pension funds merit the same criticism: the fiduciary duty to generate wealth overwhelms any intention to direct their corporate holdings in the public interest.
A better answer is to separate the two goals. The standard way to share private rewards with the broader society that made them possible is taxation. Senator Elizabeth Warren has proposed an excise tax on datacenters’ energy use. Others have proposed an AI token tax, which has much the same effect.
As to the goal of reshaping AI in the public interest, we have proposed an AI Public Option. The concept is for governments, be it federal or state, to establish publicly developed and operated AI models run by public institutions under democratic control. The idea is not to eliminate corporate AI or to seize it as a public asset, but rather for government to provide a competitive baseline that private AI offerings must meet or exceed to win business—just like the notion of a healthcare public option.
The Swiss have trailblazed this approach. Apertus is a large language model built by Swiss public servants, researchers at Swiss universities, using appropriately licensed training data and pre-existing Swiss public supercomputing infrastructure powered by renewable energy.
While Apertus doesn’t seriously compete with the latest OpenAI and Anthropic models on performance benchmarks, it blows them out of the water in transparency, sustainability and compliance with EU regulations including adherence to copyright. It’s a nascent project, but suggestive of how public institutions can apply competitive pressure for corporate actors to behave responsibly.
Don’t confuse public AI with “sovereign AI,” the notion that every country needs to invest in domestic AI infrastructure. Sovereign AI is often invoked as a marketing scheme for big tech companies looking to sell to governments; it demands public investment without guaranteeing public control.
Sanders is a bold and savvy political operator. So why is he pursuing the sovereign wealth fund strategy when he must be aware of these risks? It may be due to another argument he makes in his op-ed: that the Trump administration and the billionaire owners of AI are aligned to the idea.
It’s expedient to capitalize on rare moments of seeming alignment across diverse political factions, but it also behooves us to ask why the AI billionaires are open to this extraordinary intervention. The answer, of course, is that they believe that for every dollar ceded to government stock expropriation, they will get back more in favorable government policies to protect that newfound investment.
Energy taxation is a straightforward way to make AI companies pay for the social disruption of their technologies. Public AI represents a non-monetary mechanism for governments to shape the development of AI, complementary to direct regulation of private actors, one with a far greater chance of influencing corporate behavior towards the public interest. We urge Sanders and other political leaders to consider them.
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
Unchecked AI in the workplace quickly becomes a massive loophole for data leaks and security breaches. All too often, employees drop sensitive company data into public chatbots, or install rogue AI assistants on their own — in the process handing over way too much access. In a previous post, we broke down the different types of risky AI systems, and later shared some tips on how to turn off the built-in AI features on major tech platforms. Today let’s take a look at practical ways to block or restrict the unauthorized “helpers” employees might be using — from ChatGPT and Grammarly, to meeting bots like Fireflies and Read AI.
ChatGPT is the biggest culprit when it comes to unauthorized AI use worldwide. A quick word of warning, though: an outright ban only sends users hunting for sketchy third-party sites or messaging app chatbots that hook into the same service. That’s why it’s always a good idea to offer an approved alternative before pulling the plug.
Detecting it: keep an eye on the NGFW or web filter for traffic heading to chat.openai.com, chatgpt.com, oaistatic.com, oaiusercontent.com, or cdn.oaistatic.com. It’s also smart to use EDR/EPP tools to scan browser histories, installed apps, and browser extensions across corporate devices.
Locking it down: use the firewall or web filter to block the entire AI Services category, and set up DNS to reroute traffic away from those OpenAI domains. Browser policies can also be used to ban ChatGPT-powered extensions. Better yet, block all extensions not on a pre-approved allowlist. Finally, use application controls and EPP solutions to stop users from installing the official desktop app (ChatGPT.exe or com.openai.chat).
Detecting it: use the NGFW or web filter to track traffic going to claude.ai, anthropic.com, *.anthropic.com, and api.anthropic.com. EDR/EPP or application control tools can also be used to scan employee computers for the desktop app (claude.exe).
Locking it down: drop a blanket block on the AI Services category through the NGFW or web filter, and tweak DNS settings to reroute traffic away from the aforementioned Anthropic domains. Next, use browser policies to shut down Claude-powered extensions. Finally, use application controls and the EPP platform to prevent users from installing the desktop app.
Detecting it: keep tabs on the NGFW or web filter to flag any traffic heading to *.perplexity.ai or pplx.ai.
Locking it down: just like the others, add the AI Services category to the NGFW or web filter blocklist, and use DNS routing to redirect traffic away from those domains.
Configure the browser to block third-party extensions from being installed. If Firefox is used in the organization, be aware that recent versions come with Perplexity built in. Luckily, these AI features can be turned-off company-wide using enterprise policies — specifically, by setting SidebarChatbot = blocked. The full list of tweaks can be found in the Firefox documentation.
Detecting it: keep an eye on the NGFW or web filter for traffic hitting deepseek.com, chat.deepseek.com, api.deepseek.com, or platform.deepseek.com. For better precision, analyze the SNI (server name identification) in TLS connection requests. For mobile devices, look out for the official app (com.deepseek.chat).
Locking it down: blocklist the AI Services category on the NGFW or web filter, and reroute traffic to DeepSeek’s domains via DNS settings. Use browser policies to block third-party extensions, and lean on MDM/EMM tools to restrict the mobile app.
The playbook for these tools is exactly the same as DeepSeek, so here’s the quick list of domains to watch for and block: chat.mistral.ai, mistral.ai, console.mistral.ai, grok.com, x.ai, api.x.ai, character.ai, beta.character.ai, and c.ai.
A quick word of warning on Grok: because Grok is baked into X, blocking this specific AI access point means blocking the entire social media platform.
Detecting it: in the Slack workspace admin dashboard, look under Analytics → Slack AI usage. If an enterprise plan is used, the detailed Slack logs can be searched for any events starting with the ai_ prefix.
Blocking it with policies: in the organization’s Slack settings, click through the Workspace settings → Roles & permissions → Feature access, and change the permission to “no one”. Slack has a step-by-step guide in their help center.
Locking it down: shutting this down at the network level is tricky; it can be pulled off with a finely tuned CASB solution in place. Also, don’t forget the importance of blocking rogue integrations and keeping external AI services from tapping into Slack data in the first place. We covered how to lock this down using OAuth controls in a previous post.
Detecting it: if a corporate Zoom subscription is in use, just head to Admin Center → Reports → AI Companion usage. Detecting Zoom’s AI when employees join external meetings or use free accounts is a lot tougher, but email filters can be set up to flag incoming AI-generated meeting notes by scanning for subject lines or text containing “Meeting summary” or “Meeting assets”.
Blocking it with policies: for the company’s own Zoom subscription, go to the Admin Portal → Account Management → Account Settings → Meeting → AI Companion and toggle it OFF for everyone.
Locking it down: unfortunately, AI Companion is baked into Zoom’s DNA, so the only real option is blocking Zoom altogether.
What looks like an innocent spellchecker is actually one of the biggest culprits for workplace data leaks.
Detecting it: check the NGFW or web filter logs for traffic hitting grammarly.com, *.grammarly.com, and gnar.grammarly.com. EDR and MDM/EMM tools can also be used to hunt down the standalone desktop apps (Grammarly Desktop.exe and the macOS version), as well as the Grammarly browser extension.
Locking it down: use firewalls to block those domains at the network level, and EPP to stop employees from installing the desktop app, browser extensions, or the Grammarly add-ins for Microsoft Word and Excel.
This massive category of third-party SaaS tools records and analyzes meetings — creating a massive risk for data leaks. The trickiest part? Outside clients or vendors can bring these bots into a meeting just as easily as employees can.
Detecting them: run an audit on calendar invites, and look for bot participants using email domains like @fireflies.ai, @read.ai, @tactiq.io, @fathom.video, or @granola.ai. Zoom, Teams, or Google Meet logs can also be used to review external participants who joined past calls.
Locking them down: since it’s impossible to control what outsiders do, blocking these bots comes down to tightening meeting rules. The best moves are: blocking users from granting OAuth permissions for bots to join calls, restricting employees from inviting unapproved external participants, or locking down meeting recording access for external users. That last option is usually the least painful way to keep bots out without disrupting business.
Detecting them: use EDR/EPP tools to scan for executables like cursor.exe or windsurf.exe. It’s also worth monitoring network traffic heading to cursor.com and windsurf.com, as well as traffic hitting various AI model API providers. Keep in mind that there’s a pretty extensive list of API hosts to monitor here, since these editors aren’t tied to just one specific AI vendor.
Blocking them with policies: these apps can be prevented from being installed by setting up filters based on the developer’s digital signature certificate. Alternatively, a strict application allowlist can be employed where only pre-approved software is allowed to run.
Locking them down: rely on the EPP/EDR platform to actively detect and block these applications from running.
On one hand, this category carries fewer data leak risks because the AI models run completely locally on the user’s machine. On the other hand, it opens up a whole new can of worms: these apps themselves aren’t always highly secure, and can become targets for cyberattacks. Plus, it still means that employees can misuse models or process data in unauthorized ways.
Detecting them: EDR/EPP tools are the best line of defense here. They should be used to flag known local AI files and processes like ollama.exe, ollama serve, lmstudio.exe, LM Studio.app, jan.exe, or gpt4all.exe. From a network perspective, it’s worth scanning for open ports on local devices — typically port 1234 for Ollama and LM Studio, or port 8080 for WebUIs (using an additional fingerprint check of the server response). Another massive red flag is the presence of large files (often several gigabytes) containing language model weights. Look out for extensions like .gguf, .bin, or sometimes .safetensors.
Locking them down: use EPP/EDR platforms or windows AppLocker to block these applications by name, or switch to an application allowlist.
This is easily one of the most dangerous categories of AI tools out there. These agents mix high-level independence with access to untrusted data, making them a massive security headache.
Detecting them: use EPP/EDR tools to sniff out active processes like openclaw, nanoclaw, nemoclaw, or clawdbot. Also keep an eye out for devices running Node.js that suddenly start launching Bash or Python scripts. Another dead giveaway is the appearance of system folders like ~/openclaw, ~/nanoclaw, ~/.claw*, or ~/clawhub. At the network level, monitor connections to the AI model APIs we mentioned earlier, as well as traffic hitting servers like openclaw.ai, nanoclaw.dev, or clawhub.*.
Locking them down: the safest bet is to use strict application allowlisting (only allowing approved software to run), or to specifically ban the known agent apps listed above. On top of that, consider blocking non-developers from installing Node.js and Docker, neither of which they need on their computers anyway.
Lately, software developers have been baking AI features straight into everyday work tools, operating systems, and browsers. In some cases, they’re genuinely handy. However, their presence introduces specific risks, which means plenty of companies are hesitant to give employees access to these tools. In a previous post, we categorized these unwanted AI systems, looked at how to spot them at the network and endpoint levels, and covered the ultimate universal kill switch: managing OAuth access across major corporate platforms. In this deep dive, we’re getting tactical: breaking down how to disable or restrict the AI built into popular platforms.
A quick heads-up: major software vendors occasionally change the names of their AI settings and tweak how they function. If any of the options mentioned below are missing or aren’t working as expected, a quick web search for the setting’s name will usually point you to its new location or branding.
Detection: you can check actual Copilot usage in the logs by going to Microsoft 365 admin → Copilot usage report.
Disabling via policies: in the Microsoft 365Admin Center, go to Settings → Integrated Apps, find Copilot in the Available Apps list, and select Block. More granular configuration policies are available under Customization → Policy Management. The Policies page here contains over two thousand entries, so you’ll want to filter them by the keyword “Copilot” (detailed guide). Given that Copilot is a paid add-on for Office, another way to block it — and save money by doing so — is to simply avoid assigning users SKUs that include Copilot.
We recommend separately blocking Copilot Chat, which is available in Teams, Edge, Outlook, and several other services. Yes, it’s not Copilot itself. And yes, it has to be blocked separately by following this guide.
Additional layer of protection: you can block the domains copilot.cloud.microsoft and m365.cloud.microsoft/chat at the web filter or NGFW level. However, Microsoft explicitly advises against this, warning that it could break other Microsoft 365 features.
Beyond the Office version of Copilot, you also need to manage its consumer-facing cousin.
Detection: look through your NGFW or other network logs for traffic hitting copilot.microsoft.com, bing.com/chat, or edgeservices.bing.com.
Disabling via policies: in Windows Group Policy, navigate to Computer Config → Admin Templates → Windows Components → Windows Copilot. In Microsoft 365 Group Policy, go to Admin center → Block consumer Copilot for organizational accounts.
Additional layer of protection: block the Copilot.exe executable from running entirely.
Detection: look through your NGFW or other network logs for traffic hitting copilot.microsoft.com, bing.com/chat, or edgeservices.bing.com.
Blocking: configure the following MS Edge Group Policies: HubsSidebarEnabled = false, EdgeShoppingAssistantEnabled = false, CopilotPageContext = Disabled (false), CopilotNewTabPageEnabled = false, Microsoft365CopilotChatIconEnabled = false, GenAILocalFoundationalModelSettings = 1 (note that disabling this unexpectedly requires a 1 instead of a 0).
Second layer of protection: block the domains copilot.cloud.microsoft and m365.cloud.microsoft/chat at the web filter or NGFW level. However, Microsoft explicitly advises against this, warning that it could break other features.
Detection: check the Workspace Admin Console (admin.google.com), Gemini usage report section.
Blocking via policies: in the Admin Console, navigate to Apps → Additional Google services → > Gemini app, and set it to OFF. Then, go to Manage Workspace smart feature settings → Smart features in Google Workspace, and set it to OFF.
Second layer of protection: block network traffic to the domains gemini.google.com, bard.google.com, and aistudio.google.com.
Detection: check your Chrome Enterprise reports (Chrome management → Reports), or look through network traffic logs for connections to the previously mentioned domains.
Blocking via policies: in your Chrome Enterprise policies, configure the following settings: GenAILocalFoundationalModelSettings = 0, HelpMeWriteSettings = 2 (disabled), TabOrganizerSettings = 2, CreateThemesSettings = 2, DevToolsGenAiSettings = 2.
Additional layer of protection: block network traffic to the domains gemini.google.com, bard.google.com, and aistudio.google.com. Additionally, block unauthorized Chrome/Chromium installations (those outside your policy management) with the help of host-based application control tools like EPP/EDR or AppLocker.
Detection: on your NGFW and web filters, traffic hitting apple-relay.apple.com and *.apple-cloudkit.com is a clear indicator that Apple Intelligence is active.
Blocking via policies: any managed Apple device allows you to disable individual AI features, though there isn’t a master switch you can flip to shut down “all AI”. In your MDM profile, you need to set the following keys to false (disabled): allowWritingTools, allowMailSummary, allowGenmoji, allowImagePlayground, allowImageWand, allowPersonalizedHandwritingResults, allowExternalIntelligenceIntegrations, allowExternalIntelligenceIntegrationsSignIn, allowNotesTranscription, and allowNotesTranscriptionSummary. Here is a brief configuration example:
<dict>
<key>PayloadType</key>
<string>com.apple.applicationaccess</string>
<key>allowWritingTools</key>
<false/>
<key>allowMailSummary</key>
<false/>
</dict>
Despite Apple’s shift toward declarative device management, these AI features still need to be managed through traditional MDM payload settings.
Second layer of protection: block network traffic to the hosts mentioned above — though the obvious downside for mobile devices is that this won’t work once they leave the corporate network.
Hackers are convincing Meta’s AI support chatbot to let them take over other peoples’ accounts:
A video posted on X showed the step-by-step process to hack someone’s Instagram account. The hacker allegedly used a VPN to spoof the targets’ presumed location to avoid triggering Instagram’s automated account protections. Then, the hacker opened a chat with Meta AI Support Assistant and asked the bot to add a new email address to the target’s account. The chatbot can be seen sending a verification code to the email address provided by the hacker; the hacker then shares the verification code with the chatbot, which prompts the chatbot to show a button to “Reset Password.” The hacker enters a new password and takes over the victim’s account.
[…]
On Monday, Instagram spokesperson Andy Stone said in a reply to Wong’s post and others that the issue was now fixed. It’s unclear how many Instagram users had their accounts improperly accessed.
It’s not that easy. Probably this particular tactic is now blocked. But there are others, many others, and they cannot be blocked as a class. The real problem is that LLM chatbots are not trustworthy enough for this application.
Another news article.
Last month, Anthropic made a remarkable announcement about its new model, Claude Mythos Preview: it was so good at finding security vulnerabilities in software that the company would not release it to the general public. Instead, it would only be available to a select group of companies to scan and fix their own software.
The announcement requires context—but it contained an essential truth.
While Anthropic’s model is really good at finding software vulnerabilities, so are other models. The UK’s AI Security Institute found that OpenAI’s GPT-5.5, already generally available, is comparable in capability. The company Aisle reproduced Anthropic’s published results with smaller, cheaper models.
At the same time, Anthropic’s refusal to publicly release its new model makes a virtue out of necessity. Mythos is very expensive to run, and the company doesn’t appear to have the resources for a general release. What better way to juice the company’s valuation than to hint at capabilities but not prove them, and then have others parrot their claims?
Nonetheless, the truth is scary. Modern generative AI systems—not just Anthropic’s, but OpenAI’s and other, open-source models—are getting really good at finding and exploiting vulnerabilities in software. And that has important ramifications for cybersecurity: on both the offense and the defense.
Attackers will use these capabilities to find, and automatically hack, vulnerabilities in systems of all kinds. They will be able to break into critical systems around the world, sometimes to plant ransomware and make money, sometimes to steal data for espionage purposes, and sometimes to control systems in times of hostility. This will make the world a much more dangerous, and more volatile, place.
But at the same time, defenders will use these same capabilities to find, and then patch, many of those same systems. For example, Mozilla used Mythos to find 271 vulnerabilities in Firefox. Those vulnerabilities have been fixed, and will never again be available to attackers. In the future, AIs automatically finding and fixing vulnerabilities in all software will be a normal part of the development process, which will result in much more secure software.
Of course, it’s not that simple. We should expect a deluge of both attackers using newly found vulnerabilities to break into systems, and at the same time much more frequent software updates for every app and device we use. But lots of systems aren’t patchable, and many systems that are don’t get patched, meaning that many vulnerabilities will stick around. And it does seem that finding and exploiting is easier than finding and fixing. All of this points to a more dangerous short-term future. Organizations will need to adapt their security to this new reality.
But it’s the long term that we need to focus on. Mythos isn’t unique, but it’s more capable than many models that have come before. And it’s less capable than models that will come after. AIs are much better at writing software than they were just six months ago. There’s every reason to believe that they will continue to get better, which means that they will get better at writing more secure software. The endgame gives AI-enhanced defenders advantages over AI-enhanced attackers.
Even more interesting are the broader implications. The same searching, pattern-matching and reasoning capabilities that make these models so good at analyzing software almost certainly apply to similar systems. The tax code isn’t computer code, but it’s a series of algorithms with inputs and outputs. It has vulnerabilities; we call them tax loopholes. It has exploits; we call them tax avoidance strategies. And it has black hat hackers: attorneys and accountants.
Just as these models are finding hundreds of vulnerabilities in complex software systems, we should expect them to be equally effective at finding many new and undiscovered tax loopholes. I am confident that the major investment banks are working on this right now, in secret. They’ve fed AI the tax code of the US, or the UK, or maybe every industrialized country, and tasked the system with looking for money-saving strategies. How many tax loopholes will those AIs find? Ten? One hundred? One thousand? The Double Dutch Irish Sandwich is a tax loophole that involves multiple different tax jurisdictions. Can AIs find loopholes even more complex? We have no idea.
Sure, the AIs will come up with a bunch of tricks that won’t work, but that’s where those attorneys and accountants come in—to verify, and then justify, the loopholes. And then to market them to their wealthy clients.
As goes the tax code, so goes any other complex system of rules and strategies. These models could be tasked with finding loopholes in environmental rules, or food and safety rules—anywhere there are complex regulatory systems and powerful people who want to evade those rules.
The results will be much worse than insecure computers. Tax loopholes result in less revenue collected by governments, and regulatory loopholes allow the powerful to skirt the rules, both of which have all sorts of social ramifications. And while software vendors can patch their systems in days, it generally takes years for a country to amend its tax code. And that process is political, with lobbyists pressuring legislators not to patch. Just look at the carried interest loophole, a US tax dodge that has been exploited for decades. Various administrations have tried to close the vulnerability, but legislators just can’t seem to resist lobbyists long enough to patch it.
AI technologies are poised to remake much of society. Just as the industrial revolution gave humans the ability to consume calories outside of their bodies at scale, the AI revolution will give humans the ability to perform cognitive tasks outside of their bodies at scale. Our systems aren’t designed for that; they’re designed for more human paces of cognition. We’re seeing it right now in the deluge of software vulnerabilities that these models are finding and exploiting. And we will soon see it in a deluge of vulnerabilities in all sorts of other systems of rules. Adapting to this new reality will be hard, but we don’t have any choice.
This essay originally appeared in The Guardian.
AI security covers more than just data theft prevention, restricting rogue AI agents, or stopping assistants from giving harmful advice. A relatively simple but rapidly scaling threat has emerged: attempts to hijack computational power and exploit someone else’s neural network for personal gain. This is known as LLMjacking. With AI compute costs widely predicted to surge dramatically, the number of attackers driven by these motives is poised to grow. Consequently, when deploying proprietary AI servers and their supporting ecosystems like RAG or MCP, it’s critical to establish rigorous security measures from day one.
The speed and scale of these resource-hijacking attempts are best illustrated by an experiment documented in detail in April 2026. The investigator configured a Raspberry Pi to masquerade as a high-performance private AI server, and made it accessible from the internet. When queried, it reported the availability of Ollama, LM Studio, AutoGPT, LangServe, and text-gen-webui servers — all tools commonly used as wrappers for locally hosted AI models. The server also appeared ready to accept API requests in the OpenAI format, which has become the industry standard.
All these services were seemingly powered by a local instance of Qwen3-Coder 30B Heretic, one of the most powerful open-source models, with its safety alignment removed. To throw in a sweetener, the honeypot reported the presence of various RAG databases and an MCP server with tempting capabilities like get_credentials on board.
In reality, the Raspberry Pi was simply hosting 500 pre-saved responses from an actual Qwen3 model, with a lightweight script selecting the most relevant answer for each incoming query. This setup was enough to pass a superficial check while allowing the researcher to probe the attackers’ intentions.
According to the author, Shodan, a popular internet scanning service, discovered the server within three hours of its going live. Just one hour later, requests resembling capability reconnaissance began pouring in. Over the following month, the server handled more than 113 000 requests from thousands of unique IPs, with 23% of that traffic specifically targeted at discovering AI capabilities and exploiting local LLMs and AI agents.
Requests to endpoints like /api/tags and /v1/models allow attackers to fingerprint which models are hosted on a server, while scanning for /.cursor/rules typically precedes an attempt to exploit an AI agent. Similarly, checking /.well-known/mcp.json serves as an inventory of the victim’s MCP servers. While the author makes no mention of the total number of attacks that progressed beyond simple scanning, there were 175 active attempts to hijack the LLM during the final week of the experiment alone.
Based on the researcher’s observations, none of those targeting the decoy server attempted to execute arbitrary code or gain root access. (Editorial note: this is surprising and may point to gaps in logging.) Almost all attacks were aimed at siphoning resources. For example, the following activities were logged during the experiment:
It’s worth noting that the reconnaissance of AI resources uses standardized and rapidly evolving tools. Requests from an application named LLM-Scanner originated from the infrastructure of seven different cloud providers across eight countries, suggesting that the raiders have put established methodologies in place, as well as specialized platforms for sharing techniques. By the third week of the experiment, the scanner had been updated with an additional check: it now used simple abstract questions to determine whether it’s interacting with live AI or a honeypot returning canned responses.
Among the non-specific attacks, the experiment recorded numerous attempts to exfiltrate credentials from the .env file. Attackers systematically hunted for this file across every conceivable directory on the server. Leaving an .env file publicly accessible is one of the most elementary mistakes when deploying projects on Laravel, Node.js, and other frameworks, yet it remains a common oversight — particularly among beginners and vibe coders. Consequently, attackers have every reason to expect their efforts to pay off.
Scanning publicly accessible servers and attempting to exploit them is nothing new, but the rise of LLMs gives attackers another way to monetize their efforts — one that’s both highly lucrative for them and devastating for their victims. To understand how massive these attacks could become, look at their closest counterpart: the cryptojacking market — where criminals mine cryptocurrency using stolen computational resources. That market grew by 20% in 2025 alone. As AI-powered solutions proliferate, and as major providers hike subscription costs while local AI chips remain in short supply, we should expect LLMjacking to become an industrial-scale phenomenon.
Key defensive measures for private AI infrastructure
Turns out that LLMs are really good at hiding text messages in other text messages.
The entry barriers for app development have plummeted in recent times — with nearly anyone now able to build a professional website, personal news bot, or dashboard simply by giving a chatbot or AI agent a few instructions in natural English. Unfortunately, a massive gap exists between a slick prototype and a reliable, production-ready, secure application. To avoid becoming the subject of another AI fail story, or losing money and sensitive data, follow these straightforward tips. These are intended specifically for non-technical creators and very small teams. Larger enterprises should follow more sophisticated recommendations.
While vibe coding can deliver a seemingly functional app in just a few hours, it will likely contain dangerous flaws. AI models are trained on code samples from across the internet, which often include suboptimal tutorials, buggy snippets, and outright junk. Sometimes this code simply fails to run, but more often the situation is subtler and more hazardous: the app appears to work, yet under the hood, it might rely on a crude imitation of the required logic or contain critical vulnerabilities. According to a study by the Cloud Security Alliance AI Safety Initiative, the following facts should be considered when using AI for coding:
Always verify. Treat AI-generated code as a rough draft. It should always be reviewed and rigorously tested. Ideally, professional developers should handle this; however, if none are available, the vibe-coder should at least test the application themselves, have friends or colleagues poke around the live app, and ask them to review key code snippets. It’s also possible to evaluate code integrity by submitting a separate prompt to the AI: “Review this code for secure development best practices and check for OWASP Top 10 vulnerabilities”.
Protect secrets. Never include passwords, API keys, or any other sensitive data in AI prompts. Instead, instruct the AI to write code that securely stores all secrets in environment variables (special hidden settings).
Prioritize efforts. The main risks emerge when an application is network-accessible to outsiders, processes valuable data, or runs on infrastructure that would be useful to attackers. The components of an app or system that meet these criteria are precisely what’s needed to be protected first. A static website composed of three HTML pages faces significantly lower risk than a loyalty program integrated into an online store.
Make security an explicit requirement. Even a simple, straightforward line in the prompt, like “Follow industry standards and security best practices when generating this code”, improves the output. Providing more specific requirements for critical code snippets makes the results even better.
Don’t trust default settings. Often, the danger in vibe coding lies in the configuration rather than the code itself. For example, an app processing sensitive company data might be deployed on a public vibe-coding platform (Lovable or the like), and remain accessible to the entire internet by default. Even if the code is flawless, making that information public is a critical security failure. Because of this, every component — from hosting and database settings to the deployment pipeline — must be manually reviewed and properly configured. If the purpose of a setting is unclear, consult a chatbot for the optimal values, specifying that its goal is to enhance security, and describing who the app is intended for.
Security is a continuous process. Securing the app should not be treated as a one-off task. Every time an application is updated, hosting providers are changed, or a project undergoes any other major shift, all steps in making it secure should be revisited, and the risks reassessed.
It’s natural to want an app built from broad prompts like “Make me a beautiful, user-friendly, fast, reliable, and secure app for [use case].” However, for the results to actually be effective, each of those requirements needs to be fleshed out. Below, we’ve outlined recommendations for building standard components that will make vibe code more secure. It’s important to emphasize that “more secure” doesn’t mean “perfectly secure” — these approaches lower the risk, but that risk remains well above zero.
Demand security from the AI. When assigning a task to a neural network, be explicit: “write secure code, validate data, encrypt passwords”. Each type of task requires its own security prompt. For instance, don’t just ask to “build a login form”. Instead, ask for a “secure login form with credential validation, authentication and authorization (user permissions) controls, brute-force protection, password hashing according to modern standards, transmission strictly over HTTPS, and no hardcoded secrets”. It makes sense to use these secure requirement templates every time. It’s also helpful to keep a short cheat sheet of standard requirements for AI prompts: “validate all external data and user input before processing”, “no secrets in code”, “protect APIs from abuse”, “restrict user permissions”, and “secure default settings”.
Use off-the-shelf solutions. If an app needs a user management system, insist on using a popular, reputable library, such as NextAuth, Auth0, and so on, rather than inventing a new and vulnerable solution. This is the most common cause of data breaches. This applies to more than just login and registration; for other high-risk actions like file uploads and API call processing, it’s better to use established frameworks and libraries with built-in protections rather than building everything from scratch.
Don’t trust the AI blindly; verify open-source components. Neural networks often try to inject non-existent components and libraries into a project or suggest outdated versions. Always search for the suggested names online to ensure they are real, widely used, and secure — and make sure the latest versions are used.
Demand robust encryption. Explicitly state that modern industry standards must be used for both data transmission and storage: TLS 1.3 based on OpenSSL for network traffic; argon2 or bcrypt for hashing credentials; and so on.
Never trust user input. Always instruct the AI to include validation for any data entered by users, whether in forms or search bars. Use terms like “parameterization” and “sanitization” to emphasize that the app needs protection against malicious actors, not just users’ typos.
Set limits on user actions. Require the AI to implement rate limiting for login attempts or general requests. This will protect a project from automated attacks like DoS and brute-force password guessing.
Hide the system’s inner workings. If the site crashes, users should see a simple apology page rather than a detailed error report containing snippets of the code. That kind of information is a goldmine for hackers.
Remember that you’re a developer, and you need to protect development-related digital assets. All related accounts — such as access to GitHub, project hosting, and other resources — are prime targets for attackers. Be sure to enable two-factor authentication (2FA) on all work accounts.
Make backups. Regularly back up a project both locally and to the cloud to protect it against critical AI errors as well as cyberattacks. These backups should include both the application’s source code and its databases.
Set up a sandbox. Test new features and app versions in a secure environment using a clone of an active site or app and a copy of a database. Always run thorough tests before pushing an update live. This allows catching issues without putting users or their data at risk.
Update dependencies and scan them for vulnerabilities. A vibe-coded app will almost certainly rely on third-party libraries and components, known as dependencies. It’s wise to update these regularly by rebuilding an app with the latest versions, even if app’s code itself has not been changed. This process helps patch known security flaws in the used packages.
Check for secrets leaking into the repository. Use secrets scanners like TruffleHog to audit resulting code. Even with instructions, AI might slip up and include an API key or password in the source code. A scanner ensures that files containing keys and passwords don’t end up in Git or get published alongside the project.
What are the next steps for security leaders in this new age of frontier AI? We answer the top 10 questions customers are asking.
The post Frontier AI and the Future of Defense: Your Top Questions Answered appeared first on Unit 42.
Last week, Anthropic pulled back the curtain on Claude Mythos Preview, an AI model so capable at finding and exploiting software vulnerabilities that the company decided it was too dangerous to release to the public. Instead, access has been restricted to roughly 50 organizations—Microsoft, Apple, Amazon Web Services, CrowdStrike and other vendors of critical infrastructure—under an initiative called Project Glasswing.
The announcement was accompanied by a barrage of hair-raising anecdotes: thousands of vulnerabilities uncovered across every major operating system and browser, including a 27-year-old bug in OpenBSD, a 16-year-old flaw in FFmpeg. Mythos was able to weaponize a set of vulnerabilities it found in the Firefox browser into 181 usable attacks; Anthropic’s previous flagship model could only achieve two.
This is, in many respects, exactly the kind of responsible disclosure that security researchers have long urged. And yet the public has been given remarkably little with which to evaluate Anthropic’s decision. We have been shown a highlight reel of spectacular successes. However, we can’t tell if we have a blockbuster until they let us see the whole movie.
For example, we don’t know how many times Mythos mistakenly flagged code as vulnerable. Anthropic said security contractors agreed with the AI’s severity rating 198 times, with an 89 per cent severity agreement. That’s impressive, but incomplete. Independent researchers examining similar models have found that AI that detects nearly every real bug also hallucinates plausible-sounding vulnerabilities in patched, correct code.
This matters. A model that autonomously finds and exploits hundreds of vulnerabilities with inhuman precision is a game changer, but a model that generates thousands of false alarms and non-working attacks still needs skilled and knowledgeable humans. Without knowing the rate of false alarms in Mythos’s unfiltered output, we cannot tell whether the examples showcased are representative.
There is a second, subtler problem. Large language models, including Mythos, perform best on inputs that resemble what they were trained on: widely used open-source projects, major browsers, the Linux kernel and popular web frameworks. Concentrating early access among the largest vendors of precisely this software is sensible; it lets them patch first, before adversaries catch up.
But the inverse is also true. Software outside the training distribution—industrial control systems, medical device firmware, bespoke financial infrastructure, regional banking software, older embedded systems—is exactly where out-of-the-box Mythos is likely least able to find or exploit bugs.
However, a sufficiently motivated attacker with domain expertise in one of these fields could nevertheless wield Mythos’s advanced reasoning capabilities as a force multiplier, probing systems that Anthropic’s own engineers lack the specialized knowledge to audit. The danger is not that Mythos fails in those domains; it is that Mythos may succeed for whoever brings the expertise.
Broader, structured access for academic researchers and domain specialists—cardiologists’ partners in medical device security, control-systems engineers, researchers in less prominent languages and ecosystems—would meaningfully reduce this asymmetry. Fifty companies, however well chosen, cannot substitute for the distributed expertise of the entire research community.
None of this is an indictment of Anthropic. By all appearances the company is trying to act responsibly, and its decision to hold the model back is evidence of seriousness.
But Anthropic is a private company and, in some ways, still a start-up. Yet it is making unilateral decisions about which pieces of our critical global infrastructure get defended first, and which must wait their turn.
It has finite staff, finite budget and finite expertise. It will miss things, and when the thing missed is in the software running a hospital or a power grid, the cost will be borne by people who never had a say.
The security problem is far greater than one company and one model. There’s no reason to believe that Mythos Preview is unique. (Not to be outdone, OpenAI announced that its new GPT-5.4-Cyber is so dangerous that the model also will not be released to the general public.) And it’s unclear how much of an advance these new models represent. The security company Aisle was able to replicate many of Anthropic’s published anecdotes using smaller, cheaper, public AI models.
Any decisions we make about whether and how to release these powerful models are more than one company’s responsibility. Ultimately, this will probably lead to regulation. That will be hard to get right and requires a long process of consultation and feedback.
In the short term, we need something simpler: greater transparency and information sharing with the broader community. This doesn’t necessarily mean making powerful models like Claude Mythos widely available. Rather, it means sharing as much data and information as possible, so that we can collectively make informed decisions.
We need globally co-ordinated frameworks for independent auditing, mandatory disclosure of aggregate performance metrics and funded access for academic and civil-society researchers.
This has implications for national security, personal safety and corporate competitiveness. Any technology that can find thousands of exploitable flaws in the systems we all depend on should not be governed solely by the internal judgment of its creators, however well intentioned.
Until that changes, each Mythos-class release will put the world at the edge of another precipice, without any visibility into whether there is a landing out of view just below, or whether this time the drop will be fatal. That is not a choice a for-profit corporation should be allowed to make in a democratic society. Nor should such a company be able to restrict the ability of society to make choices about its own security.
This essay was written with David Lie, and originally appeared in The Globe and Mail.
Login
