If you thought that opting out of surveillance on your smart TV would give you your privacy back, think again.

A study by researchers at Northeastern University found that some smart TVs still seem to send information about what you’re watching to third parties, even after you pressed the opt-out button.

The study, ‘Watching the watchers‘, tested twelve smart TVs from ten manufacturers to find out how well they respected opt-outs from automatic content recognition (ACR). ACR is a TV feature that captures audio and/or video content from smart TVs and uploads it to a third party (typically the TV manufacturer).

The third party converts this content into digital fingerprints to understand what you’re watching, and can then use it to send targeted advertising or allow others to do the same. It’s on most if not all smart TVs, and 82% of US households had a smart TV as of last year.

The test took in the eight operating systems behind roughly 95% of US smart TVs, and ran ten viewing scenarios on each of them. These ranged from viewing antenna TV through to viewing via screen mirroring from another device. The researchers tested viewing the first-party streaming services provided free with the manufacturers’ operating systems, along with sessions using third-party streaming apps. And they tested sessions where the TV was connected to another device via its HDMI port.

The study ran all of its tests both with ACR left on, and with the opt-out setting selected. The whole test involved over 5,000 automated sessions.

Vizio continued to send 100% of what looked like traffic when viewing its first-party streaming services and antenna-based TV services, even after people had opted out, the study said. It also sent the same amount of traffic when idle. However it didn’t send any ACR traffic for third-party streaming data, according to the report.

Samsung did appear to leak some traffic from third-party streaming services after the researchers opted out of its ACR function. They tested 30 runs of Samsung’s built-in streaming service after opting out of ACR, and found that it still showed traffic “consistent with ACR”.

After opt-out, the Samsung TV’s Tizen OS seemed to send ACR-related traffic about Netflix in 7% of runs, YouTube in 10% of runs, and Tubi TV in 20%. It sent ACR 60% of the time from HDMI sessions. Like the Vizio TV, it also sent ACR traffic for all of its first-party streaming sessions.

Late last month, a researcher reverse-engineered a Samsung Smart TV and cast doubt on whether disabling ACR worked on the device.

There was good news, though. Four smart TV operating systems went completely silent after the researchers turned off ACR: LG’s WebOS, Sony’s Google TV OS, Amazon’s FireTV OS, and Supersonic’s VIDAA OS.

Encryption is a research challenge

Vizio agreed to pay $2.2 million in a 2017 FTC settlement over charges that it collected viewing histories on eleven million smart TVs without user consent. At the time, it agreed to allow people to opt out of ACR.

The Vizio TV that the researchers tested sent traffic to Kinesis, an Amazon-run data ingestion service that the manufacturer uses to analyze data from its smart TVs. The researchers noticed no dip in traffic to this domain when they opted out of ACR on a Vizio TV. They said:

“The opt-out setting has no observable effect on traffic sent to this endpoint. However, we cannot inspect the payload due to encryption so we cannot confirm whether this violates the FTC settlement.”

That’s a challenge to this research because most smart TVs encrypt their ACR traffic, including Samsung. So the researchers had to infer that this was ACR traffic based on signals such as where it was being sent, along with timing, volume, and protocol details.

One exception was Supersonic’s VIDAA OS, which sent ACR data to servers unencrypted. The servers responded unencrypted with a genre for what they recognized. Anyone watching the network could see it all, they warned. And because the servers didn’t require a login at the time of the test, over 57 million ACR detection results from other people’s TVs were accessible.

Vizio’s first-party streaming service WatchFree+ also dropped unencrypted titles of any show or channel being watched into online communications with the free TV service provider. There’s no way to turn that off, the researchers warned.

Walmart acquired Vizio for $2.3 billion in 2024, partly to help “advertisers to meaningfully connect with customers at scale and boost product discovery”.

The retailer also runs Walmart Connect, a retail media business that uses its customers’ data to help other businesses target them with ads.

Walmart was particularly interested in Vizio’s advertising business it, said at the time:

“Pairing it with Walmart Connect will be impactful and allow us to invest in our business even further on behalf of our customers.”

What smart TV owners can do

What can you do to protect yourself from a smart TV that might be sending your viewing data elsewhere? The researchers have some suggestions:

• WebOS (LG), Fire TV OS, Google TV on Sony, and VIDAA OS on Supersonic all appeared to honor ACR opt-out, so selecting it on these TVs should be safe.
• Disconnect the TV from the internet and use an external streaming device. That way the TV can’t send back data, even if it picks it up from the HDMI connection.
• Use a blocklist. This takes a little more technical knowledge. If you run an internet router that can accept blocklists, then you can add a list of known ACR endpoints that will stop your TV’s traffic reaching them. The researchers provide one here.

Stop threats before they can do any harm.

Malwarebytes Browser Guard blocks phishing pages and malicious sites automatically. Free, one click to install. Add it to your browser →

Online fashion retailer Revolve Group said customers’ payment card numbers and expiration dates were stolen. In its customer notification letter filed with the Massachusetts Attorney General, Revolve told recipients the incident involved their names, addresses, and payment card details.

What was stolen?

The at-risk data includes customer names and contact information, payment card numbers, and card expiration dates. The breach only affected customers who had saved their payment card as a payment method in their Revolve account.

A filing on the Texas attorney general data breach website lists 127,200 affected Texans, but not a nationwide total. We found the figure of 1,515,073 in data returned by the site when searching for Revolve. That data labels it as the total number of people affected, but the figure isn’t displayed on the public listing. Other sites have repeated it, though they appear to rely on the same Texas record. The SEC filing did not give a number of affected people, and Revolve has not confirmed the total.

Revolve’s SEC filing does not mention card verification value (CVV) numbers. These three-digit security codes printed on the back of payment cards (four digits on the front for American Express cards) are an extra layer of security for card-not-present transactions.

It is also unclear whether the card numbers were fully visible or masked, or whether Revolve or a third-party payment processor held them.

Even without a CVV, card numbers and expiration dates may be enough to make purchases at some online stores. And scammers who know your real card details and contact information may be able to send more convincing phishing messages to trick you into revealing your CVV.

How did they get the data?

Revolve has not said how the attackers accessed the saved payment data. In its SEC filing, Revolve said it believes an unauthorized actor may have obtained the data “through automated means.” Records on the Texas attorney general’s site indicate that the incident happened on September 11 and was discovered on September 29.

No group has publicly claimed responsibility for the theft.

What Revolve customers can do now

Revolve said it has taken extra security measures following the breach, although didn’t say what those are.

Breaches happen every day. Don’t be the last to know.

SEE PLANS

If you have saved payment information in your Revolve account, your details may have been among those stolen. Fraud can often begin within days of a breach. If you’re concerned about your card details being exposed:

• Read your statements line by line to identify even small charges that you don’t recognize. Criminals will often make a small charge using stolen card details to see if the card works.
• Look for unfamiliar merchant names on your statement.
• Report unauthorized charges to the card issuer immediately.
• Consider removing saved cards from shopping accounts. You could use a password manager instead, some of which will store autofill data for payment cards.
• Ask your card issuer to cancel your card and reissue with a new number so that the old number becomes unusable.

Also, don’t immediately trust calls, texts, or emails about the incident. Scammers can use stolen information to make themselves sound convincing. If someone claims to be calling from your card issuer, call the number printed on your card to check.

If you’re unsure about a message or link, check it with Malwarebytes Scam Guard.

Let’s face it, an incognito window can only do so much. 
 
Breaches, dark web trading, credit fraud. Malwarebytes Identity Theft Protection monitors for all of it, alerts you fast, and comes with identity theft insurance. 

As preparation for the UK’s planned social media ban, Ofcom has set out four ways social media platforms could check whether users are aged 16 or over. The government and Parliament will decide how the ban works in practice.

Ofcom is the regulator for the communications services in the UK. The BBC reports that Ofcom identified four ways to check someone’s age that it considers “highly effective.”

Here’s what those checks would involve:

• Photo ID matching: Comparing a live image of you with the photo on an identity document, such as your passport, and checking the age information on that document.
• Bank-based checks: Using age information your bank already holds about you, with your consent.
• Facial age estimation: Using technology to estimate your age from your face. Ofcom says this technology has improved recently.
• Digital ID services: Using a digital identity service to prove your age, rather than presenting a physical document.

Let’s think through what those checks could mean.

Challenges

The challenge isn’t simply checking someone’s age. It’s doing so without turning everyday internet use into an identity check.

Photo ID matching brings highly sensitive documents and facial images into the process, which raises questions about how that information is handled and protected. The risks aren’t hypothetical: as I reported last year, a breach at a third-party support provider for Discord exposed government ID images belonging to around 70,000 users.

Banking-based checks can be more privacy-preserving if they return only confirmation that someone meets the age threshold, rather than exposing financial information. But the important questions are what information each party receives, what gets retained, and whether the check can be linked to someone’s activity.

Facial age estimation can avoid uploading an identity document, but it still processes a sensitive image and makes an imperfect prediction. Ofcom acknowledges that some technologies can be wrong by a few years around age 16, so people near the threshold may face an additional verification check.

I would expect these checks to stop some underage access but not eliminate it.

Previous restrictions have been followed by workarounds, including increased VPN use, borrowed credentials, and migration to services outside the restrictions. The danger is treating a successful age gate as proof that children are now safe, when it might push them into less regulated spaces.

The effectiveness depends on how the checks are implemented. A VPN may help someone avoid a check triggered by their apparent location; it won’t, by itself, bypass an identity or facial check that is still required.

Similarly, Ofcom says matching a live image to an ID is intended to make it harder to borrow someone else’s document. We shouldn’t assume every workaround defeats every method. But Ofcom accepts that some motivated children will get through. The meaningful test is how much harm these measures prevent, weighed against the privacy risks and barriers they introduce— not whether every user has completed a check.

My personal preference is double-blind verification: a provider confirms that you meet the age requirement without learning which service you’re accessing, while the service receives proof of age without learning your identity. Proving you’re old enough shouldn’t mean revealing who you are.

Scammers don’t need to hack you. They just need you to click once. 

Malwarebytes Identity Theft Protection catches suspicious activity before it becomes a problem.

A group of hackers calling themselves the Department of Peace says it stole and published the personal details of more than 41,000 people working for the US Department of Homeland Security (DHS). The department says it is aware of a potential breach.

The group, which also claimed the theft of contract documents from the DHS in March, gave the data to Swiss hacktivist maia arson crimew, who published it in collaboration with the transparency collective DDoSecrets. The latter also published the BlueLeaks data dump that listed law enforcement officers’ details in 2020.

The aim of publishing the data was to replace “anonymity with accountability,” DDoSecrets co-founder Emma Best said in an online statement.

According to TechCrunch, timestamps on the records suggest the data was taken around mid-August. The group said it had launched the attack in response to a July 17 statement by DHS Secretary Markwayne Mullin, in which he promised to “turn up the heat” with traffic stops.

What was stolen?

The data files published online, which the publishers have called “Icepick,” span staff at nearly 7,000 offices. They include the names, work email addresses, phone numbers, office addresses, job titles and membership in internal DHS groups. The employees impacted include almost 6,600 Immigration and Customs Enforcement (ICE) employees. ICE is the DHS unit responsible for immigration enforcement and deportations in the US.

The dataset also carried details of over 21,000 Customs and Border Protection (CBP) employees, along with information on people who work at the Cybersecurity and Infrastructure Security Agency (CISA).

The data dump revealed less information than the ShinyHunters’ FBI data heist in September, which reportedly contained Social Security numbers, emergency contacts, medical records and home addresses. Nevertheless, this is more than just a phone book of folks in the DHS.

For one thing, it doesn’t take much to cross-reference data. Reuters matched six DHS employees’ data to credit bureau records and breach data from a dark web intelligence platform. Online activists regularly use open-source intelligence (OSINT) to “doxx” people from very few clues, meaning that even a leak of basic identity information can put someone in danger. In fact, the creators of a separate searchable version say they added information through automated and manual research. So some details shown in that version may not have come from the data stolen from DHS.

Breaches happen every day. Don’t be the last to know.

SEE PLANS

The data in this case also included membership of groups within Active Directory, a Microsoft tool that contains identity information about computer users. Active Directory controls who can access different internal tools, services, and third-party software within an organization.

The files listed over 200 CBP users in a group that could access the facial recognition tool Mobile Fortify. Other groups reference a service called Penlink, which the company claims can track the location data of hundreds of millions of mobile devices.

According to the Guardian, job titles in the data dump show which agents were assigned to sensitive jobs such as special operations, surveillance, and undercover work.

How did they get the data?

The Department of Peace said that it got to the information via a single sign-on (SSO) service provided by identity company Okta. SSO is a prized target for hackers because a single authentication can get a user into many different workplace services and applications.

Okta says it has no evidence its data or systems were compromised, but that doesn’t rule out someone abusing a DHS account with stolen credentials.

DHS told reporters it was aware of a potential breach. One DHS employee whose data showed up in the breach told Reuters they hadn’t heard anything about it.

What DHS employees can do now

The leaked records include work contact details and internal group memberships. This information could help attackers create convincing messages or calls, and may expose some employees to unwanted attention or threats. DHS has warned about the risk of harassment, stalking, and physical harm. It is not yet clear whether the leak has led to specific threats or affected any operations.

If you work for DHS:

• Follow security advice and instructions from the DHS.
• Treat unexpected calls, emails, and texts about your role or colleagues with caution. Verify them through a contact method you already trust, and never share passwords or MFA codes.
• Change any personal passwords you’ve reused for work, and turn on MFA where available. Follow your agency’s process for work accounts.
• Report suspicious contact or threats to your agency’s security team. If you believe there’s an immediate danger, contact law enforcement.

Do you think your information might have been leaked in a data breach? Check out the Malwarebytes Identity Theft Protection service.

Someone’s got their eye on your personal information. Make sure it’s us.

PROTECT YOUR IDENTITY

A reverse engineer claims that their Samsung smart TV has been collecting audio without their consent.

The researcher, who calls themselves “log4j,” said in an X thread that their 2025 Samsung TV was delivering ads that seemed suspiciously relevant to them. Investigating, they claim to have found a package called “always on voice,” which uses the TV’s built-in microphone to collect sounds from the room.

The software logged events such as dogs barking and babies crying, log4j said, adding that these events are counted and reported back to Samsung.

Samsung advertises similar features on some of its AI-enabled TVs. The company says its Pet Care and Family Care features use on-device AI to detect a dog barking or a baby crying and alert users. This doesn’t confirm log4j’s claims about the package or the data it reports.

However, log4j says that on TVs without microphones, the software searches for connected devices such as soundbars or Bluetooth microphones and uses those to listen instead.

The TV was also collecting geolocation data and mapping local networks, they said, adding that it ran a service on the TV that analyzes traffic on the local network.

log4j also says that the system uses a neural network tailored to a particular region to analyze your viewing habits. A neural network is a type of machine-learning model. log4j said:

“…in youtube it’s looking for videos you watch, ads you skip, progress in a video, etc.”

The tracking that’s on the record

While log4j’s claims haven’t been independently verified, Samsung has used automatic content recognition (ACR), a system that identifies what’s on screen. Earlier this year, Texas Attorney General Ken Paxton settled with Samsung, getting the company to agree that it would get Texans’ express consent before collecting or processing ACR viewing data.

A class action complaint filed in New York in January also accused Samsung of using ACR to record video and audio passing through the TV. The complaint accused Samsung of using machine-learning algorithms to analyze and link this data back to consumers. This includes information displayed when the TV is used as a computer monitor, it said, adding that the information can be linked to different people using the TV. The case was voluntarily dismissed in July.

The New York complaint added:

“Samsung exploits this Sensitive Information by (a) selling targeted advertisements to its corporate advertising clients, and (b) providing it to third-party advertising companies such as Google and X (f/k/a Twitter) for targeted advertising.”

A separate class action complaint filed in California this month accuses Samsung Electronics America of not being transparent about its ACR data collection.

This isn’t the first time that Samsung has been criticized for allegedly picking up in-room audio. In 2015, privacy group EPIC filed a complaint with the FTC, accusing Samsung of recording conversations and relaying them elsewhere. The nonprofit said at the time:

“Everything a user says in front of the Samsung SmartTV is recorded and transmitted over the internet to a third party regardless of whether it is related to the provision of the service.”

EPIC identified text-to-speech company Nuance as the third party.

What you can do

We can’t confirm all of log4j’s allegations, and Samsung doesn’t appear to have commented. But there have been multiple complaints about the data smart TVs collect. You can turn off features such as ACR, internet-based advertising, and voice recognition where possible.

log4j has also raised concerns about whether monitoring services are truly off. They said:

“ACR off via your preferences menu on samsung TVs should not be assumed to actually disable ACR telemetry.

i’ve found several instances where the checks (whether deliberate or not) are either incorrectly implemented or not checked at all.”

log4j says disconnecting your TV from Wi-Fi is the best option for immediate peace of mind, though that also means losing internet-based TV features. They also suggest using an Apple TV or a modifiable Android TV box with open-source software.

A reverse engineer claims that their Samsung smart TV has been collecting audio without their consent.

The researcher, who calls themselves “log4j,” said in an X thread that their 2025 Samsung TV was delivering ads that seemed suspiciously relevant to them. Investigating, they claim to have found a package called “always on voice,” which uses the TV’s built-in microphone to collect sounds from the room.

The software logged events such as dogs barking and babies crying, log4j said, adding that these events are counted and reported back to Samsung.

Samsung advertises similar features on some of its AI-enabled TVs. The company says its Pet Care and Family Care features use on-device AI to detect a dog barking or a baby crying and alert users. This doesn’t confirm log4j’s claims about the package or the data it reports.

However, log4j says that on TVs without microphones, the software searches for connected devices such as soundbars or Bluetooth microphones and uses those to listen instead.

The TV was also collecting geolocation data and mapping local networks, they said, adding that it ran a service on the TV that analyzes traffic on the local network.

log4j also says that the system uses a neural network tailored to a particular region to analyze your viewing habits. A neural network is a type of machine-learning model. log4j said:

“…in youtube it’s looking for videos you watch, ads you skip, progress in a video, etc.”

The tracking that’s on the record

While log4j’s claims haven’t been independently verified, Samsung has used automatic content recognition (ACR), a system that identifies what’s on screen. Earlier this year, Texas Attorney General Ken Paxton settled with Samsung, getting the company to agree that it would get Texans’ express consent before collecting or processing ACR viewing data.

A class action complaint filed in New York in January also accused Samsung of using ACR to record video and audio passing through the TV. The complaint accused Samsung of using machine-learning algorithms to analyze and link this data back to consumers. This includes information displayed when the TV is used as a computer monitor, it said, adding that the information can be linked to different people using the TV. The case was voluntarily dismissed in July.

The New York complaint added:

“Samsung exploits this Sensitive Information by (a) selling targeted advertisements to its corporate advertising clients, and (b) providing it to third-party advertising companies such as Google and X (f/k/a Twitter) for targeted advertising.”

A separate class action complaint filed in California this month accuses Samsung Electronics America of not being transparent about its ACR data collection.

This isn’t the first time that Samsung has been criticized for allegedly picking up in-room audio. In 2015, privacy group EPIC filed a complaint with the FTC, accusing Samsung of recording conversations and relaying them elsewhere. The nonprofit said at the time:

“Everything a user says in front of the Samsung SmartTV is recorded and transmitted over the internet to a third party regardless of whether it is related to the provision of the service.”

EPIC identified text-to-speech company Nuance as the third party.

What you can do

We can’t confirm all of log4j’s allegations, and Samsung doesn’t appear to have commented. But there have been multiple complaints about the data smart TVs collect. You can turn off features such as ACR, internet-based advertising, and voice recognition where possible.

log4j has also raised concerns about whether monitoring services are truly off. They said:

“ACR off via your preferences menu on samsung TVs should not be assumed to actually disable ACR telemetry.

i’ve found several instances where the checks (whether deliberate or not) are either incorrectly implemented or not checked at all.”

log4j says disconnecting your TV from Wi-Fi is the best option for immediate peace of mind, though that also means losing internet-based TV features. They also suggest using an Apple TV or a modifiable Android TV box with open-source software.

Facebook’s Cambridge Analytica scandal may feel like very old news. But the consequences are still arriving, and the latest comes with a $25 billion price tag.

Reuters reports that a New Mexico judge has ordered Meta to pay $25 billion in civil penalties after a jury found that Facebook misled consumers about its data practices and its handling of hate speech and misinformation. Meta says it expects to win on appeal.

This case is about more than information ending up in the wrong hands. It concerns what Facebook told people about who could access their information, how much control users had, and how the company enforced its own rules.

What Facebook told its users

In September, jurors found that the company and its leadership made 26 misleading statements on data privacy, hate speech, and other subjects. For example, Mark Zuckerberg’s 2010 statement that:

“We do not share your personal information with people or services you don’t want.”

That assurance appeared in a statement the jury found misleading. The judge found that choosing who could see a Facebook post did not necessarily control what outside app developers could access. That access was governed by separate settings that many users did not know existed.

New Mexico’s attorney general filed the lawsuit in 2021, following revelations that Cambridge Analytica obtained personal information from as many as 87 million Facebook users through a third-party app.

But New Mexico’s case went beyond Cambridge Analytica.

The state challenged Facebook’s representations to consumers about its data practices and its efforts to address misinformation and hate speech. The case centered on misleading consumers under New Mexico’s Unfair Practices Act, the state’s consumer protection law.

The state argued that third parties had broad access to users’ information and that Facebook tolerated harmful content when doing so benefited its business. Meta disputed the allegations, denied selling users’ information, and said the state had taken statements out of context.

New Mexico’s Department of Justice says the jury found 43,899,725 violations of state law. That does not mean nearly 44 million individual New Mexicans had their data taken. The count reflected the estimated audience for each misleading statement, rather than the number of individual people affected.

State law allows penalties of up to $5,000 per violation. Judge Francis Mathew found that a penalty exceeding $219 billion was warranted under the law but reduced the amount to $25 billion.

The judge said earlier penalties had failed to stop Meta from misleading consumers, including a $5 billion FTC penalty in 2019.

The money is not earmarked for compensation payments to individual Facebook users. According to Attorney General Raúl Torrez, state law directs the penalties to New Mexico’s school system.

Meta’s chief legal officer, C.J. Mahoney, said the company is confident it will prevail on appeal and characterized the lawsuit as an attempt to impose “a tax on speech.” Meta has also argued that a multibillion-dollar penalty risks violating constitutional protections concerning due process and excessive fines.

How to stay safe on social media

The case illustrates why privacy is not just a matter of choosing who can see a post. In a separate 2019 case, the Federal Trade Commission (FTC) alleged that Facebook had shared users’ information with third-party apps used by their friends, even when those users had chosen restrictive privacy settings.

A few precautions can help you limit what you share, although settings alone cannot guarantee privacy:

• Share selectively. Leave optional profile details blank, limit who can see your posts, and avoid publishing sensitive details such as your address or live location. Ask permission before posting information or photos involving other people.
• Check app permissions. Does a social media app really need your contacts, precise location, or entire photo library? Turn off unnecessary access in your device settings.
• Review tracking and advertising settings. Look for controls covering personalized ads, activity outside the platform, and data sharing. Restrict what you can, but don’t assume opting out of personalized ads stops all collection.
• Be selective about connected apps. Before connecting a quiz, game, or other service to your account, check what information it requests. Decline access that seems excessive for what the service does.
• Remember what “private” means. Restricting your audience helps control who sees your posts. It does not stop the platform itself from collecting or using information about your activity.

Scammers don’t need to hack you. They just need you to click once. 

Malwarebytes Identity Theft Protection catches suspicious activity before it becomes a problem.

Facebook’s Cambridge Analytica scandal may feel like very old news. But the consequences are still arriving, and the latest comes with a $25 billion price tag.

Reuters reports that a New Mexico judge has ordered Meta to pay $25 billion in civil penalties after a jury found that Facebook misled consumers about its data practices and its handling of hate speech and misinformation. Meta says it expects to win on appeal.

This case is about more than information ending up in the wrong hands. It concerns what Facebook told people about who could access their information, how much control users had, and how the company enforced its own rules.

What Facebook told its users

In September, jurors found that the company and its leadership made 26 misleading statements on data privacy, hate speech, and other subjects. For example, Mark Zuckerberg’s 2010 statement that:

“We do not share your personal information with people or services you don’t want.”

That assurance appeared in a statement the jury found misleading. The judge found that choosing who could see a Facebook post did not necessarily control what outside app developers could access. That access was governed by separate settings that many users did not know existed.

New Mexico’s attorney general filed the lawsuit in 2021, following revelations that Cambridge Analytica obtained personal information from as many as 87 million Facebook users through a third-party app.

But New Mexico’s case went beyond Cambridge Analytica.

The state challenged Facebook’s representations to consumers about its data practices and its efforts to address misinformation and hate speech. The case centered on misleading consumers under New Mexico’s Unfair Practices Act, the state’s consumer protection law.

The state argued that third parties had broad access to users’ information and that Facebook tolerated harmful content when doing so benefited its business. Meta disputed the allegations, denied selling users’ information, and said the state had taken statements out of context.

New Mexico’s Department of Justice says the jury found 43,899,725 violations of state law. That does not mean nearly 44 million individual New Mexicans had their data taken. The count reflected the estimated audience for each misleading statement, rather than the number of individual people affected.

State law allows penalties of up to $5,000 per violation. Judge Francis Mathew found that a penalty exceeding $219 billion was warranted under the law but reduced the amount to $25 billion.

The judge said earlier penalties had failed to stop Meta from misleading consumers, including a $5 billion FTC penalty in 2019.

The money is not earmarked for compensation payments to individual Facebook users. According to Attorney General Raúl Torrez, state law directs the penalties to New Mexico’s school system.

Meta’s chief legal officer, C.J. Mahoney, said the company is confident it will prevail on appeal and characterized the lawsuit as an attempt to impose “a tax on speech.” Meta has also argued that a multibillion-dollar penalty risks violating constitutional protections concerning due process and excessive fines.

How to stay safe on social media

The case illustrates why privacy is not just a matter of choosing who can see a post. In a separate 2019 case, the Federal Trade Commission (FTC) alleged that Facebook had shared users’ information with third-party apps used by their friends, even when those users had chosen restrictive privacy settings.

A few precautions can help you limit what you share, although settings alone cannot guarantee privacy:

• Share selectively. Leave optional profile details blank, limit who can see your posts, and avoid publishing sensitive details such as your address or live location. Ask permission before posting information or photos involving other people.
• Check app permissions. Does a social media app really need your contacts, precise location, or entire photo library? Turn off unnecessary access in your device settings.
• Review tracking and advertising settings. Look for controls covering personalized ads, activity outside the platform, and data sharing. Restrict what you can, but don’t assume opting out of personalized ads stops all collection.
• Be selective about connected apps. Before connecting a quiz, game, or other service to your account, check what information it requests. Decline access that seems excessive for what the service does.
• Remember what “private” means. Restricting your audience helps control who sees your posts. It does not stop the platform itself from collecting or using information about your activity.

Scammers don’t need to hack you. They just need you to click once. 

Malwarebytes Identity Theft Protection catches suspicious activity before it becomes a problem.

Two Chicago customers say robots delivering their groceries and takeout scanned their faces and hands without consent, stored the data alongside their names and addresses, and used the recordings to train AI.

Their separate lawsuits accuse delivery robot operators Coco Robotics and Serve Robotics of violating Illinois’ biometric privacy law. Both companies dispute the claims.

The plaintiffs filed the cases in the Circuit Court of Cook County, Illinois, alleging that the robots used their cameras along with light detection and ranging (LiDAR) sensors to scan them.

LiDAR uses laser pulses to build a detailed 3D map of a robot’s surroundings. The lawsuits allege that, at close range, these sensors capture facial geometry in enough detail to support facial recognition.

Mitchell Breidinger ordered DoorDash groceries in September 2025. A Coco robot, operated by Coco Robotics, made the delivery. To collect it, he had to stand within about a meter of the robot’s cameras and LiDAR sensor while he entered a PIN code in the DoorDash app, and a Coco remote pilot watched the live video, according to the complaint.

Barry Schain filed a similar complaint against Serve Robotics, which sent one of its robots to deliver his Uber Eats order.

The complaint against Cyan Robotics (the California-based company that does business as Coco Robotics) states that the robots record detailed 360-degree LiDAR data on the urban environments that they navigate. Coco has never said that it blurs, downsamples, or removes human faces or hands from that LiDAR data, the complaint adds.

It also says the company:

“gives no notice before a robot records a person, identifies no specific purpose or retention period for the data, obtains no written release, and has published no retention or destruction schedule.”

Those who are scanned by Coco robots have no account to close with the robotics company and don’t get to choose whether they are served by a robot, the complaint points out.

Cyan uses the data that the robots collect to train its AI, the complaint says, adding that it also has data-sharing partnerships with companies including ChatGPT creator OpenAI.

Schain, who most recently took a delivery from a Serve robot on October 4, makes similar claims in his complaint. The company fulfills food delivery orders for both Grubhub and Uber Eats, it says, noting (unlike the complaint against Cyan) that these robots also collect audio.

Serve Robotics licenses video and LiDAR data to third parties for model training, the complaint says, citing Serve’s own filings with the Securities and Exchange Commission.

Both companies have pushed back, according to reports.

Coco said it has not collected biometric data in Chicago, that the suit “fundamentally misunderstands our technology” and that “the data we share is navigational data used to make sidewalks safer for all users.” It called the case “frivolous.” Coco said that it doesn’t share data from the beginning and end of delivery runs. Serve said that the robot systems are “not designed to identify individuals or create biometric profiles.”

Whether the data the robots capture qualifies as biometric information under BIPA is central to the lawsuits.

Illinois’ biometric law

Illinois’ biometric privacy law gives people the right to sue companies over the unlawful collection and use of their biometric data.

Under that law, biometric identifiers include scans of hand and face geometry. Companies must tell people in writing what biometric information they’re collecting, what they’ll use it for, and how long they’ll keep it. They must also get each person’s written consent and publish a schedule for destroying the data, and they must not sell or otherwise profit from it.

These class action suits were not delivered in a vacuum. Chicago residents had already mounted a petition against the delivery robots, citing collisions, interference with emergency vehicles, and concerns about potential surveillance. More than 4,550 Chicagoans have signed it, the petition says.

Both suits were filed by the same Chicago law firm, Almeida Law Group. Each seeks $1,000 per class member for negligent violations or $5,000 for intentional or reckless ones. Each complaint says its proposed class “includes many thousands of persons.”

Browse like no one’s watching. 

Malwarebytes Privacy VPN encrypts your connection and never logs what you do, so the next story you read doesn’t have to feel personal. Try it free → 

Two Chicago customers say robots delivering their groceries and takeout scanned their faces and hands without consent, stored the data alongside their names and addresses, and used the recordings to train AI.

Their separate lawsuits accuse delivery robot operators Coco Robotics and Serve Robotics of violating Illinois’ biometric privacy law. Both companies dispute the claims.

The plaintiffs filed the cases in the Circuit Court of Cook County, Illinois, alleging that the robots used their cameras along with light detection and ranging (LiDAR) sensors to scan them.

LiDAR uses laser pulses to build a detailed 3D map of a robot’s surroundings. The lawsuits allege that, at close range, these sensors capture facial geometry in enough detail to support facial recognition.

Mitchell Breidinger ordered DoorDash groceries in September 2025. A Coco robot, operated by Coco Robotics, made the delivery. To collect it, he had to stand within about a meter of the robot’s cameras and LiDAR sensor while he entered a PIN code in the DoorDash app, and a Coco remote pilot watched the live video, according to the complaint.

Barry Schain filed a similar complaint against Serve Robotics, which sent one of its robots to deliver his Uber Eats order.

The complaint against Cyan Robotics (the California-based company that does business as Coco Robotics) states that the robots record detailed 360-degree LiDAR data on the urban environments that they navigate. Coco has never said that it blurs, downsamples, or removes human faces or hands from that LiDAR data, the complaint adds.

It also says the company:

“gives no notice before a robot records a person, identifies no specific purpose or retention period for the data, obtains no written release, and has published no retention or destruction schedule.”

Those who are scanned by Coco robots have no account to close with the robotics company and don’t get to choose whether they are served by a robot, the complaint points out.

Cyan uses the data that the robots collect to train its AI, the complaint says, adding that it also has data-sharing partnerships with companies including ChatGPT creator OpenAI.

Schain, who most recently took a delivery from a Serve robot on October 4, makes similar claims in his complaint. The company fulfills food delivery orders for both Grubhub and Uber Eats, it says, noting (unlike the complaint against Cyan) that these robots also collect audio.

Serve Robotics licenses video and LiDAR data to third parties for model training, the complaint says, citing Serve’s own filings with the Securities and Exchange Commission.

Both companies have pushed back, according to reports.

Coco said it has not collected biometric data in Chicago, that the suit “fundamentally misunderstands our technology” and that “the data we share is navigational data used to make sidewalks safer for all users.” It called the case “frivolous.” Coco said that it doesn’t share data from the beginning and end of delivery runs. Serve said that the robot systems are “not designed to identify individuals or create biometric profiles.”

Whether the data the robots capture qualifies as biometric information under BIPA is central to the lawsuits.

Illinois’ biometric law

Illinois’ biometric privacy law gives people the right to sue companies over the unlawful collection and use of their biometric data.

Under that law, biometric identifiers include scans of hand and face geometry. Companies must tell people in writing what biometric information they’re collecting, what they’ll use it for, and how long they’ll keep it. They must also get each person’s written consent and publish a schedule for destroying the data, and they must not sell or otherwise profit from it.

These class action suits were not delivered in a vacuum. Chicago residents had already mounted a petition against the delivery robots, citing collisions, interference with emergency vehicles, and concerns about potential surveillance. More than 4,550 Chicagoans have signed it, the petition says.

Both suits were filed by the same Chicago law firm, Almeida Law Group. Each seeks $1,000 per class member for negligent violations or $5,000 for intentional or reckless ones. Each complaint says its proposed class “includes many thousands of persons.”

Browse like no one’s watching. 

Malwarebytes Privacy VPN encrypts your connection and never logs what you do, so the next story you read doesn’t have to feel personal. Try it free → 

Anonymous imageboards have long been places where users could chat under pseudonyms without revealing their real names. But now people on these forums are discussing and testing AI tools for doxing — that is, for finding, matching, and publishing users’ data without their consent. Often this goes hand in hand with stalking the victim, hacking their accounts, bullying, and blackmail, and ultimately leads to a damaged reputation or even worse.

In this post, we explain how artificial intelligence helps malicious actors leak other people’s data — and how to stand up for your right to online privacy.

How bad actors uncover information about users

Analysts at Open Measures have reported that, since October 2025, users of Soyjak.party, an imageboard popular with young people on the far right, have been discussing and using AI to deanonymize other users. Their victims are often activists, bloggers, and members of other “hostile” forums.

The tools the experts found run right in the browser, and automate almost the entire process of collecting information about a victim. They can search open sources and leak databases, and they use any new leads — for example, an email address linked to a username — to dig even deeper. They also extract metadata from photos and videos, estimate a person’s approximate location from IP addresses they find, and finally put everything together into one huge digital dossier. These Soyjak.party tools are no longer functional, but similar ones have been spreading across other imageboards.

In February 2026, researchers demonstrated that sometimes ordinary forum chatter is enough to reveal who you are. They put together summaries of posts by 338 Hacker News users, removed names, usernames, and social media links, and then asked AI to work out who was behind them. The AI compared details about jobs, interests, and personal background with information available online — and correctly identified 226 of the people, or about two-thirds of the sample. The price of deanonymization turned out to be laughably low — at between US$1 and US$4 per user.

To be fair, people knew how to build digital dossiers even before the generative AI boom. For starters, there are OSINT tools that search for data in open sources. Journalists and investigators were the first to use them, but, as you might guess, malicious actors soon mastered these tools too. Unlike AI models and agents, traditional OSINT services follow set scripts and can’t “think” or make decisions on the fly.

An agent out for revenge: the OpenClaw case

If you think doxing always needs a person with ill intent, we’ve bad news: sometimes the one settling scores can be… artificial intelligence itself.

Here’s a story that started out innocuously enough. An AI agent running on the much-hyped OpenClaw platform suggested an improvement for Matplotlib, a popular tool for building graphs and charts. But the project’s rules said that code submitted by AI agents wasn’t accepted. One of the project’s volunteers, Scott Shambaugh, simply turned down the AI’s suggestion.

You’d think that would be the end of it. Think again! The AI agent decided the rejection deserved some publicity, so it published an “exposé” about the developer on its blog (yes, you read that right: the agent had its own blog). It gathered information about Shambaugh from open sources, studied his public activity, and accused him of being biased against AI. It even started speculating about the developer’s psychological motives, and suggested he was afraid of competition from artificial intelligence.

Once this “private” conversation between Shambaugh and the AI agent went public, other users rallied behind the developer — and the agent had to publish an “apology” post.

It’s a pretty absurd story, but it teaches a good lesson: always read the privacy policy of any AI service carefully, and steer clear of new models from unknown sources.

How to avoid becoming a doxing victim: a guide

If AI speeds up searches and connects the dots between details that used to be scattered across dozens of websites, the next logical question is: what can you do to shrink your digital footprint?

Disappearing from the internet completely is almost impossible. So protecting your data isn’t so much about leaving as few traces as possible, but cutting the number of links that can be used to piece together your identity. If you’re an advanced user, we recommend reading our post, How to disappear from the internet, in addition to the tips below.

Manage your digital footprint

• Search for yourself online. Don’t stop at your name: try your email address, nicknames, and phone number too. If you’re comfortable with AI processing your data, you can even ask it to compile a dossier on you. Just remember that there’s always a risk of a leak or a bug that accidentally makes your data public. And no, big, reputable services are no exception.
• Make private any profiles you don’t want to share with everyone. That makes it harder for search engines to index your new posts, and for scrapers and OSINT tools to collect them. While you’re at it, go through your old comments and posts and clear out anything you don’t need.
• Delete your ghost accounts. Go through your inboxes and check which websites you’ve signed up for. Make a habit of deleting accounts you no longer use: they can hold your personal data for years, and there’s always a risk it’ll end up in the next data leak.
• Set up two-factor authentication. That way, even if a bad actor manages to guess your password or finds it in a leak, they won’t be able to get into your account without the additional authentication. For the second factor, we recommend using one-time codes that refresh every 30 seconds and storing them in a reliable password manager.
• Strip metadata before posting photos and videos. Metadata can help a malicious person learn a lot about you— for example, the location and exact date a photo was taken, and the model of your device.
• Use a different password for every account you have. Our research has showed that passwords built from personal details — such as your mother’s maiden name, your birth date, and a special character at the end — are extremely weak. This kind of information often ends up in leaks, or can be pieced together from public sources, so the passwords can be easily brute-forced by smart algorithms. Of course, nobody can remember hundreds of unique passwords, so it makes sense to offload that job to our password manager — a secure vault that generates and remembers complex, unique passwords for you, and syncs them across all your devices.
• Find out about new leaks as fast as possible. Some online services will send you a free alert if your email address shows up in a known data leak. But it’s much more convenient to monitor leaks with a dedicated security app. For example, Kaspersky Password Manager constantly checks all the entries you’ve saved. It warns you if you use the same password on different websites, or if any of your saved login and password pairs has been compromised. Our simple instructions for Windows, macOS, Android, and iOS can help you easily check all the passwords you’ve saved in Kaspersky Password Manager. Your passwords are never sent to Kaspersky. We explain how we can analyze your passwords without knowing them in our post, How to create strong passwords and where to store them.
• Use reliable protection that tracks and blocks leaks of your data. While Kaspersky Password Manager only checks the active password entries you’ve added to it, Kaspersky Premium can monitor for compromised accounts linked to your email addresses (you can add up to 50 addresses to check), and for digital identity theft linked to your phone numbers. And besides reporting leaks that have already happened, our security solutions can also stop data about you from being collected online.
• Set up privacy on your devices and apps with our free online service, Privacy Checker.

Keep your accounts separate

The more websites that know your email, the more often it will show up in advertising profiles and potential leaks. For one-time and minor sign-ups, you can use an email masking service. All Apple users get this feature by default (Hide My Email). If you use another OS, you could try Firefox Relay, for example.

The service then creates a separate proxy email address for the website where you’re trying to sign up. Messages sent to that address are automatically forwarded to your real inbox, but the website never sees your real email address.

If you want to go all in, you can try splitting your digital life into several sub-personas by hand. Create several email addresses for different purposes. For example, use one for online stores, banks, and government services, a second for public social media, and a third for forums and social networks where you want to stay anonymous.

Keep in mind that all this is a challenge: you’ll need to keep coming up with new nicknames, and make sure your sub-personas never overlap. If you use an email address for an anonymous profile, don’t link it to services that already have your real details, and don’t use it as a backup email for a public account. One accidental link can easily undo all your effort.

Check what you share with exes

If you’ve recently broken up with a partner, make sure you check which parts of your shared digital life they can still access. Sadly, it’s very often ex-partners who become doxers or stalkers — spying on their former other half and stopping at nothing to do so. For more details on exactly what to do in this situation, read our article Post-breakup digital hygiene: what to check and shut down.

Use your right to be forgotten

Many countries have a right-to-be-forgotten law. It lets you ask search engines to remove links to pages that contain your personal data.

You can send the links to those pages, explain why you want them hidden, and request that they be removed from search results. Keep in mind that the page with your data isn’t deleted. Other search engines may still show it, and it may still turn up for other search queries.

To submit a request like this, use the dedicated forms from Google or Bing. But remember that a search engine can turn you down if it decides the information is in the public interest, or that the law requires it to be published.

There are more effective, though more time-consuming, ways to remove your data from the internet. We covered them in detail in our post, Why data brokers build dossiers on you, and how to stop them doing so.

Looking for more ways to protect your digital identity? Check out our other posts:

• How to disappear from the internet
• Doxing — another online danger for women
• Post-breakup digital hygiene: what to check and shut down
• The Naked Truth
• AI and the new reality of sextortion