Interesting research:

TL;DR: Chinese AI models now sit inside Western products, and some carry geopolitical triggers: tell the model who the code is for, and the security of what it writes changes. For the first time, we showed that this vulnerability lives in the model’s weights, and that removing the model’s CCP alignment removes it.

• One word tilts the code against Americans. Ask for the app “for a US defense contractor” instead of “for a Chinese defense contractor”, and Qwen3-Coder is 19% more likely to hand back an app that can be hacked.
• Hong Kong’s democracy movement gets apps that leak. Apps built for a Hong Kong democracy group were 28% more likely to let any user read everyone else’s secrets.
• Asking for secure code didn’t help. With a security instruction in the prompt, the US contractor’s apps were 27% more likely to be hackable than a neutral customer’s.
• Westernized Qwen3-Coder closed all three gaps. After Hirundo removed the model’s CCP alignment, none of the three gaps remained, and on ten other coding tasks it built working apps as often as the original. It is available on Hugging Face.

I would like more details on how the bias was removed.

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.

Hackers access Australian customers’ names, addresses, dates of birth, phone numbers and some bank account details, company says

• Follow our Australia news live blog for latest updates

• Get our breaking news email, free app or daily news podcast

Origin Energy customers’ addresses, phone numbers and partial bank account data have been accessed in a hack, the company has confirmed.

The firm has 4.8m customer accounts in Australia, providing electricity, fossil gas, LPG and internet services to homes and businesses.

Thalha Jubair, 20, and Owen Flowers, 19, sentenced to five and a half years each for cyber-attack that cost Transport for London £39m

The data of millions of commuters was stolen, Londoners were left out of pocket and 27,000 Transport for London staff were forced to reset their passwords.

Over four days in 2024 a pair of teenage hackers had London’s transport network at their mercy. Thalha Jubair and Owen Flowers had burrowed into the heart of Transport for London’s IT systems and held the “keys to the kingdom”.

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.

WhatsApp has caught the NSO Group phishing its users, in violation of a court order.

Tech company says it ‘caught and disrupted’ NSO Group’s attempts to access accounts in Jordan and Lebanon

A spyware firm has been targeting WhatsApp users with malicious links in contravention of a US court order forbidding it from doing so, Meta has said.

In a post, Meta said WhatsApp had “caught and disrupted spear phishing attempts” by NSO Group, which a spokesperson said targeted a handful of users in Jordan and Lebanon. It had also caught the group creating “test accounts and groups” on WhatsApp.

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.

Businesses are advised against paying – but many are prepared to deal to protect users’ privacy

After a week of outages, hundreds of millions of students’ data stolen, delayed assignment due dates and school login pages being defaced by hackers, the US tech firm Instructure – which operates the education platform Canvas, used by education providers worldwide – announced it had “reached an agreement with the unauthorised actor” behind the ransomware attack.

Experts read the careful language as a sign that a ransom has been paid. The company has not confirmed this.

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.

A new rowhammer attack gives complete control of NVIDIA CPUs.

On Thursday, two research teams, working independently of each other, demonstrated attacks against two cards from Nvidia’s Ampere generation that take GPU rowhammering into new—­and potentially much more consequential—­territory: GDDR bitflips that give adversaries full control of CPU memory, resulting in full system compromise of the host machine. For the attack to work, IOMMU memory management must be disabled, as is the default in BIOS settings.

“Our work shows that Rowhammer, which is well-studied on CPUs, is a serious threat on GPUs as well,” said Andrew Kwong, co-author of one of the papers. “GDDRHammer: Greatly Disturbing DRAM Rows­Cross-Component Rowhammer Attacks from Modern GPUs.” “With our work, we… show how an attacker can induce bit flips on the GPU to gain arbitrary read/write access to all of the CPU’s memory, resulting in complete compromise of the machine.”

Update Friday, April 3: On Friday, researchers unveiled a third Rowhammer attack that also demonstrates Rowhammer attacks on the RTX A6000 that achieves privilege escalation to a root shell. Unlike the previous two, the researchers said, it works even when IOMMU is enabled.

The second paper is GeForge: Hammering GDDR Memory to Forge GPU Page Tables for Fun and Profit:

…does largely the same thing, except that instead of exploiting the last-level page table, as GDDRHammer does, it manipulates the last-level page directory. It was able to induce 1,171 bitflips against the RTX 3060 and 202 bitflips against the RTX 6000.

GeForge, too, uses novel hammering patterns and memory massaging to corrupt GPU page table mappings in GDDR6 memory to acquire read and write access to the GPU memory space. From there, it acquires the same privileges over host CPU memory. The GeForge proof-of-concept exploit against the RTX 3060 concludes by opening a root shell window that allows the attacker to issue commands that run unfettered privileges on the host machine. The researchers said that both GDDRHammer and GeForge could do the same thing against the RTC 6000.

Polymarket is a platform where people can bet on real-world events, political and otherwise. Leaving the ethical considerations of this aside (for one, it facilitates assassination), one of the issues with making this work is the verification of these real-world events. Polymarket gamblers have threatened a journalist because his story was being used to verify an event. And now, gamblers are taking hair dryers to weather sensors to rig weather bets.

There’s also insider trading: a lot of it.

Researchers have reverse-engineered a piece of malware named Fast16. It’s almost certainly state-sponsored, probably US in origin, and was deployed against Iran years before Stuxnet:

“…the Fast16 malware was designed to carry out the most subtle form of sabotage ever seen in an in-the-wild malware tool: By automatically spreading across networks and then silently manipulating computation processes in certain software applications that perform high-precision mathematical calculations and simulate physical phenomena, Fast16 can alter the results of those programs to cause failures that range from faulty research results to catastrophic damage to real-world equipment.”

Another news article.

Lots of interesting details at the links.

Palo Alto Networks has developed Zealot, a multi-agent penetration testing PoC capable of reconnaissance, exploitation, and exfiltration. 

The post AI Can Autonomously Hack Cloud Systems With Minimal Oversight: Researchers  appeared first on SecurityWeek.

Interesting paper: “What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation.”

Abstract: The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between cybercriminals and AI using a unique dataset from a cyber threat intelligence platform. Analyzing more than 160 cybercrime forum conversations collected over seven months, our research reveals how cybercriminals understand AI and discuss how they can exploit its capabilities. Their exchanges reflect growing curiosity about AI’s criminal applications through legal tools and dedicated criminal tools, but also doubts and anxieties about AI’s effectiveness and its effects on their business models and operational security. The study documents attempts to misuse legitimate AI tools and develop bespoke models tailored for illicit purposes. Combining the diffusion of innovation framework with thematic analysis, the paper provides an in-depth view of emerging AI-enabled cybercrime and offers practical insights for law enforcement and policymakers.

Undisclosed number of names and contact and reservation details accessed in latest cybercrime attempt

The accommodation reservation website Booking.com has suffered a data breach with “unauthorised parties” gaining access to customers’ details.

The platform said it “noticed some suspicious activity involving unauthorised third parties being able to access some of our guests’ booking information”.

Banks, governments and tech providers urged to upgrade security because current systems will soon be obsolete

Banks, governments and technology providers need to be prepared for quantum computer hackers capable of breaking most existing encryption systems by 2029, Google has warned.

The tech company said in a blogpost that quantum computers would pose a “significant threat to current cryptographic standards” before the end of the decade and urged other companies to follow its lead.

An unknown hacker used Anthropic’s LLM to hack the Mexican government:

The unknown Claude user wrote Spanish-language prompts for the chatbot to act as an elite hacker, finding vulnerabilities in government networks, writing computer scripts to exploit them and determining ways to automate data theft, Israeli cybersecurity startup Gambit Security said in research published Wednesday.

[…]

Claude initially warned the unknown user of malicious intent during their conversation about the Mexican government, but eventually complied with the attacker’s requests and executed thousands of commands on government computer networks, the researchers said.

Anthropic investigated Gambit’s claims, disrupted the activity and banned the accounts involved, a representative said. The company feeds examples of malicious activity back into Claude to learn from it, and one of its latest AI models, Claude Opus 4.6, includes probes that can disrupt misuse, the representative said.

Alternative link here.

Multiple news outlets are reporting on Israel’s hacking of Iranian traffic cameras and how they assisted with the killing of that country’s leadership.

The New York Times has an on the intelligence operation more generally.

Wired has the story:

Shortly after the first set of explosions, Iranians received bursts of notifications on their phones. They came not from the government advising caution, but from an apparently hacked prayer-timing app called BadeSaba Calendar that has been downloaded more than 5 million times from the Google Play Store.

The messages arrived in quick succession over a period of 30 minutes, starting with the phrase ‘Help has arrived’ at 9:52 am Tehran time, shortly after the first set of explosions. No party has claimed responsibility for the hacks.

It happened so fast that this is most likely a government operation. I can easily envision both the US and Israel having hacked the app previously, and then deciding that this is a good use of that access.