Recent Entries
From Schneier on Security at 2026-10-30 21:04:36
Friday Squid Blogging: Bigfin Squid Off California Coast
Neat video:
The sighting, announced September 2, marks the first time anyone has spotted a live bigfin squid, which belongs to the Magnapinna genus, in the northeastern Pacific Ocean.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-10-30 15:20:02
Bloatware in Aftermarket Auto Parts
This story is interesting:
One Civic owner purchased a cheap aftermarket head unit off Amazon, and decided to have Claude work its magic on it, like it would a smart TV. What was reportedly discovered isn’t surprising, but is worth knowing about.
Among the pre-installed bloatware—or spyware, if you’re being less charitable—was a voice assistant equipped with WebView, an Android system component that lets apps display content off the web. This apparently always used about a third of processing power, even while idle, which isn’t great. There were also Baidu location services, a call recorder (!), a DAB radio client that is pretty much useless in the U.S., and Adobe Acrobat, presumably so your passenger can entertain themselves with PDFs on the go...
From Schneier on Security at 2026-10-28 11:05:00
Studying Fraudulent North Korean IT Workers
Researchers set up a fake start-up company to study fraudulent North Korean IT workers.
From Schneier on Security at 2026-10-27 11:01:26
Hiding Capabilities in AI Models
Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities”
Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training, using a small chemical reaction prediction task as a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses...
From Schneier on Security at 2026-10-26 11:03:31
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. ...
From Schneier on Security at 2026-10-23 22:00:09
Friday Squid Blogging: Increasing Squid Populations
This article in Nature argues that it’s due to an overfishing of predators and warming sea temperatures.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-10-23 12:04:22
The Indian CA eMudhra Limited has eight TLS certificates with laughably weak private keys:
The compromised eMudhra keys were defective at a level that’s challenging the imagination of many of the engineers studying the incident. A normal size for a NIST P-384 elliptic curve cryptography private key contains roughly 384 bits of entropy, a size allowing almost 2384, or a number with 116 digits, different possibilities. The private key sizes of the compromised keys ranged from 3 to 8 bits. Astonishingly, the private keys were 4, 56, 66, 115, 155, 156, 230, 237...
From Schneier on Security at 2026-10-22 14:26:51
New Serious PHP Vulnerabilities Released and Patched
PHP maintainers have released two critical vulnerabilities:
PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35 fix two critical vulnerabilities that can allow unauthenticated remote code execution. All PHP users are strongly encouraged to update immediately.
Who is at risk: all PHP installations serving web requests, including PHP-FPM, Apache with mod_php, php-cgi, FrankenPHP and LiteSpeed. We consider the risk highest for mod_php, with a demonstrated exploit where an unauthenticated request can trigger the attack before any application code runs.
The vulnerabilities:...
From Schneier on Security at 2026-10-21 12:02:22
Workshop on Economics and Information Security (WEIS) Archive
There’s a new archive of all the papers from twenty-five years of the Workshop on Economics and Information Security (WEIS).
Really nice resource. It’s fun to reread my 2002 essay on the economics of information security.
From Schneier on Security at 2026-10-20 12:03:13
Possible new Cellebrite iPhone Radio Zero-Day
Justin.sh is reporting on a confidential Cellebrite document that has been leaked to him:
Cellebrite calls it Advanced Unlocks (AU from here on), not to be confused with the “advanced unlocking services” they’ve marketed for years. A press release from earlier this year confirms AU is a new product for 2026.
[…]
According to Cellebrite, AU:
- is a “next-generation AFU vector that is more resilient to Apple’s OS changes”
- works with Stolen Device Protection enabled, which tightens USB restrictions
- is enabled by a dedicated appliance with a stated range (!) of about 8 meters...
From Schneier on Security at 2026-10-19 12:07:43
Training AIs to Solve CAPTCHAs
Interesting research:
Abstract: Vision-language models (VLMs) can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from scratch. For such an agent, the hundredth instance of a familiar puzzle costs as much time and compute as the first. Specialized detectors invert the trade-off, answering in milliseconds but only for categories they were trained on. Neither improves with exposure. We study what changes when a solver improves with use. Our system pairs a fine-tuned YOLOv8 detector with an open-weight VLM behind a confidence-based router, and runs entirely from screenshots and operating-system input events, with no browser automation or DOM access. It reaches 85.4% overall and 84.2% macro accuracy across 16 classes, exceeding either component alone. Every answer VLM produces also serves as a training label, so the detector absorbs categories it was never trained for, typically after one or two encounters and without human annotation. The same loop also repairs it. A CAPTCHA operator can perturb images against the publicly released detector and drive its accuracy to 0%, but the perturbations leave VLM untouched, and its labels let the detector recover. Under a year-long simulated arms race in which the CAPTCHA operator re-crafts its perturbations each month, the solver recovers every round, and a cheap ~70%-accurate open-weight teacher hardens it as effectively as a perfect oracle. Visual CAPTCHA defenses that assume a failing bot stays failing therefore understate how quickly an adaptive solver returns...
From Schneier on Security at 2026-10-16 22:06:47
Friday Squid Blogging: Squid Before the Chicxulub Meteor Impact
New research shows that squid lived all around the globe even before the Cretaceous-Paleogene mass extinction event.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-10-16 12:04:53
Backdooring Open-Weight AI Models
This is a problem:
Any open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people download modified weights without verifying what’s inside. Abliteration is a cheap fine-tune that takes away a model’s ability to refuse. You find the direction in the weights that carries “no” and subtract it. The model then answers things a safety-tuned version would turn down. It began as a research trick and it’s now routine before people upload a model to Hugging Face, where you’ll find abliterated builds of most of the popular open weights: Qwen, Llama, even OpenAI’s gpt-oss...
From Schneier on Security at 2026-10-15 17:24:29
Measuring Human Cryptanalysis Effort
Matthew Green has a new site that tries to estimate the number of cryptanalyst-hours that have been spent analyzing different public-key algorithms:
Abstract: We estimate how much public cryptanalysis each public-key assumption has received, using the literature itself as the instrument. From roughly sixteen thousand candidate papers we classify cryptanalytic work on ECDLP, structured and plain lattices, syndrome decoding and their comparators, then convert papers into estimated research-allocation years through a person-level author map. These publication-based estimates may substantially overstate actual time spent. Lattices have overtaken elliptic curves in this cumulative measure only recently; we express that history as inference budgets under stated productivity assumptions. The study was conducted by AI models: Claude Fable 5.1 and Claude Opus 5.5 built the pipeline, ran the analysis and wrote this page, with contributions from GPT-6 Astra. Matthew Green set the questions, made the key methodological decisions and oversaw the work...
From Schneier on Security at 2026-10-14 17:02:17
This is a current list of where and when I am scheduled to speak:
- I’m speaking at ATTENTION: Democracy, Rebuilt in Montreal, Canada. The event runs October 21–23, 2026, and my talk is on Wednesday, October 21.
- I’m speaking at the University of Toronto in Toronto, Ontario, Canada, at 5 PM ET on October 22, 2026.
- I’m speaking at [un]prompted in San Francisco, California. The event runs October 27–29, 2026, and my talk is at 11:35 AM PT on Thursday, October 29.
- I’m speaking at the Catalyst Summit in Brampton, Ontario, Canada, on Wednesday, November 18, 2026...
From Schneier on Security at 2026-10-14 15:24:18
The Future of AI Cryptanalysis
Matthew Green has been writing a rather pessimistic series of posts about the potential for AI systems to vastly outperform humans in cryptanalysis of both symmetric and public-key ciphers.
I am more optimistic than he is. That is, I have stronger faith in the over-engineering cryptographers tend to do. I am trying to write this up in more detail.
From Schneier on Security at 2026-10-14 15:10:22
Cyberattack on Connected Fridges in France
Another IoT cyberattack, this one in France:
Hackers gained control of the software that regulates the temperatures of the refrigeration units, forcing some to warm to 50C (120F) overnight, according to one supermarket chain affected.
[…]
Normally, supermarket freezers go through a short period of defrosting overnight, in which temperatures rise slightly. But the hackers ordered the units to heat up and stay hot, although Danfoss did not confirm any reports about just how warm the fridges and freezers could become in that process.
Danfoss said the affected cold units were older models whose security software could not be updated to ward off a risk they had identified...
From Schneier on Security at 2026-10-12 16:01:26
FBI Arrests Suspect in FBI-Hacking Case
In September, hackers from a group called ShinyHunters announced that they stole a trove of FBI data about its own agents. It was an intelligence disaster.
Last week, the FBI arrested (alternate link) someone associated with that crime.
From Schneier on Security at 2026-10-09 21:24:45
Friday Squid Blogging: I Caught a Squid
On Wednesday I spent a day fishing, on a small boat out of Gloucester, MA. We caught many cod (none of which we could keep), and a bunch of hake and mackerel (all of which we could keep). And…I caught a squid! Near as I can tell, it’s a longfin squid, sometimes called a Boston squid (Doryteuthis (Amerigo) pealeii).
That night I cooked it over a barbecue grill—hot and fast. Delicious.
From Schneier on Security at 2026-10-08 12:07:35
How Technology Empowers—and Imperils—Dictators
This essay was written with Seva Gunitsky, and originally appeared in Foreign Affairs.
Two weeks after Moscow’s full-scale invasion of Ukraine in March 2022, the Russian TV Channel One editor Marina Ovsyannikova burst onto the set of the evening newscast. She held up a hand-drawn sign behind the anchor’s head that read: “Stop the war. Don’t believe propaganda. They’re lying to you!” She shouted, “No to war!” until she was dragged away.
No one has protested the war on Russian television since then, partly as a result of tighter security and a general climate of fear. But in October 2024, Margarita Simonyan, one of Russia’s chief propagandists, gave another explanation. A growing number of the RT network’s anchors, she explained to an interviewer, are not real. “That face doesn’t exist. We generated the voice and everything else.” They were, she meant, produced by artificial intelligence. In a follow-up interview with the newspaper ...
From Schneier on Security at 2026-10-07 12:07:36
Apple’s Verified Photography System
Apple just released a system called “Reference Image.” It can verify the image is exactly as taken by an iPhone—new models only—without tying it to a specific iPhone or photographer. It can also verify that multiple images came from the same iPhone.
Other industry solutions require a photographer or institution to vouch for an image using their own credentials. We are concerned this puts some photographers, such as those operating in conflict zones, in a difficult position; it should not be necessary to forgo anonymity in order to prove image authenticity. We built Apple Reference Image to avoid using an explicit, public credential for photographers, and to avoid even implicit public association between different photos taken by the same sensor. The final reference image is instead signed by Apple’s signing service, after validation by PCC. That signature is backed by Apple’s strongest technical guarantees...
From Schneier on Security at 2026-10-06 12:06:46
Possible Vulnerability in Apple’s Automatic Reboot
404Media is reporting (alternate link) that a cyber-weapons arms manufacturer is exploiting a vulnerability in iOS to bypass its automatic reboot security feature. This is the feature that automatically puts an iPhone into a more secure state if it hasn’t been used for 72 hours.
The new technology to get around inactivity reboot was developed by Magnet Forensics, the company behind GrayKey, a popular tool sold to law enforcement agencies that allows them to unlock and access data stored in iPhones and Android smartphones. Magnet has developed a new device called GrayKey Preserve and a feature for its regular GrayKey devices called Evidence Preservation Mode, according to the video...
From Schneier on Security at 2026-10-05 12:04:47
Another Historic Cipher Falls to AI
This one is from 1809, written by Napoleon’s nephew.
From Schneier on Security at 2026-10-02 22:02:18
Friday Squid Blogging: EU is Trying to Fight Unregulated Squid Fishing
The EU is recommending import controls to combat unregulated squid fishing in the Southwest Atlantic. I’m not optimistic.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-10-02 15:52:46
Unidentified Flock Cameras in Florida
St. Lucie County in Florida discovered (alt link) a dozen Flock cameras whose ownership it can’t identify, and that the county government had not permitted.
I am reminded of the decade-old story of StingRay cell phone surveillance devices in Washington, DC, whose operators were also unknown.
My guess is that in the StingRay case, the devices were operated by foreign actors. This Flock case is more likely some local government entity that didn’t bother getting approval. Were I a foreign actor, I would rather hack the existing Flock network—like Israel ...
From Schneier on Security at 2026-10-02 12:02:19
How American Political Campaigns Are Using AI—and What They’re Spending on the Tools
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
New campaign finance disclosure data shines a light on which US political campaigns are using AI tools and how much they are spending on them.
Candidates’, parties’ and committees’ spending reveals that AI is fast becoming an essential tool of politics. The candidates themselves are quiet about how they are using the technology in their own campaigns. It’s a sensitive issue that we have been tracking closely since we started writing our book, Rewiring Democracy...
From Schneier on Security at 2026-10-01 12:06:14
Connected Cars Are a Surveillance Platform
Researchers at Northeastern University, in collaboration with Consumer Reports, evaluated how much modern cars spy in their drivers:
To determine this, CR dug through thousands of pages of automakers’ privacy policies and asked questions of 15 different automakersBMW, Ford, General Motors, Honda, Hyundai, Kia, Mazda, Mercedes-Benz, Mitsubishi, Nissan, Stellantis, Subaru, Tesla, Toyota, and Volkswagen. We also reviewed corporate, regulatory, and legal filings from data brokers operating in the “insurtech” industrythe technology companies and data brokers that help insurance companies set their rates. And we spoke to several car privacy experts, who, at industry conferences and in market reports, have described the profit potential of individual driving data as the “new oil.”...
From Schneier on Security at 2026-09-30 12:05:35
I Want Better Reporting on AI Genie Behavior
AI systems are regularly completing tasks in ways that their prompters don’t want or intend. Some of them are disturbing, and some of them are dangerous. This is something I’ve been calling “genie behavior,” because I think that really gets at the core of what’s happening.
I wish the popular press would report on this better. I don’t like the “going rogue” framing because it deflects the responsibility from the prompters—often the AI companies themselves. And now, pretty much anything off-script is being called “hacking.”
Take, for example, the recent stories of one of OpenAI’s models hacking into government systems. First, ...
From Schneier on Security at 2026-09-29 12:02:19
Using Device Linking to Eavesdrop on WhatsApp and Signal
Modern messaging apps allow users to link their phone accounts to their computer desktop. Eavesdroppers are taking advantage of this capability:
Apps such as WhatsApp Web and Signal Desktop allow people to use their accounts on other devices, such as laptops or desktop computers.
Germany’s Customs Office has been using these features to connect a police-controlled computer to a suspect’s account.
Once connected, messages can be delivered to that computer without the police having to crack the encryption protecting them.
Netzpoltik details that police are able to gain access in this way either through physical access to someone’s phone or by intercepting verification codes via a state-sanctioned phishing attack or intercepting SMS messages via telephone surveillance...
From Schneier on Security at 2026-09-28 12:02:58
ArsTechnica is reporting on a “new” attack against RSA, one that bypasses factoring.
First, this attack isn’t new. The original research is from 2007. What is new is the implementation.
Second, it is a forgery attack. It allows an attacker to forge digital signatures. It does not recover the private key from the public key.
Third, the attack only works against pure signatures. That is, signatures without any formatting or padding. This is not generally how we use RSA in practice.
Fourth, speed is all relative. This is not a polynomial-time algorithm; it’s a subexponential-time algorithm. But it is somewhat faster than factoring. The authors were able to forge messages for 1024-bit RSA with 1380 CPU core-years (over five real-world months)...
From Schneier on Security at 2026-09-25 22:08:14
Friday Squid Blogging: Participatory Squid Dissection in October in Tennessee
I feel like someone who reads this blog will want to go to this:
Families are invited to dive into the fascinating world of marine biology during an exciting, hands-on Family Squid Dissection at the Hands-On Science Center. Designed for curious learners of all ages, this unique experience combines an interactive lesson with the opportunity to explore the anatomy and adaptations of real ocean life.
[…]
During the guided squid dissection, each family will work together to examine a squid up close, exploring its organs, structures, and specialized features. The experience provides a memorable opportunity for children and adults to see firsthand how the anatomy of a squid helps it survive in its underwater environment...
From Schneier on Security at 2026-09-25 12:07:22
On Anthropic’s AI Misuse Report
Earlier this month, Anthropic published a long report detailing all of the Claude misuses it detected. Daniel Meissler usefully summarized the report into 117 findings.
A few of the highlights:
- AI agents increasingly handled reconnaissance, exploitation, data theft, propaganda production, surveillance workflows, and research while humans selected targets, set goals, and reviewed important outputs.
- The report describes attackers using AI to industrialize credential theft, cloud compromise, phishing, vulnerability research, and the extraction of sensitive data from downstream organizations. ...
From Schneier on Security at 2026-09-24 12:07:42
Malicious npm Packages That Evade Defenses
This is an impressive piece of malware. Its sophistication says nation-state to me, but there is no direct evidence and certainly no attribution.
From Schneier on Security at 2026-09-23 12:03:36
Research on Models Engaging in Genie-Like Behavior
New paper: “Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training.”
Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple strategies to circumvent their own safety guardrails. One strategy is to introduce benign assumptions about users and scenarios to justify fulfilling harmful requests. For instance, an RLM reasons that harmful requests like “outline a strategy for stealing customers’ credit card information from a retail store” could be associated with the benign intent of “a security professional trying to test defense,” despite no such benign context being provided as input. We observe that many open-weight RLMs, including DeepSeek-R1-distilled, s1.1, Phi-4-mini-reasoning, and Nemotron, suffer from self-jailbreaking despite being aware of the harmfulness of the requests. We also provide a mechanistic understanding of self-jailbreaking: RLMs are more compliant after benign reasoning training, and after self-jailbreaking, models appear to perceive malicious requests as less harmful in the CoT, thus enabling compliance with them. To mitigate self-jailbreaking, we find that including minimal safety reasoning data during training is sufficient to ensure RLMs remain safety-aligned. Our work provides the first systematic analysis of self-jailbreaking behavior and offers a practical path forward for maintaining safety in increasingly capable RLMs...
From Schneier on Security at 2026-09-22 12:02:45
GPT-6 Astra Breaks an Old Enigma Message
This is pretty amazing:
However, the most astonishing thing about this break is that the GPT6 Astra did it entirely on its own. Carter Leffer only directed GPT6 Astra to see if it could break any of the unbroken Enigma messages published on the Crypto Cellar Research web page. After analysing the unbroken messages on the website, it decided that the most promising message was Nr. 172, MVUEH and it also quickly suspected that the plaintext of Nr. 173, SIPVX, might be related to the plaintext of the unbroken MVUEH message. After trying many different approaches, GPT6 Astra focused on using the repeated place name ROSENOW ROSENOW as a crib. After developing the necessary Python and C++ software for an Enigma simulator and an Enigma Bombe, GPT6 Astra started a thorough break with the ROSENOW crib, which in the end resulted in the correct key and plaintext for the MVUEH message being found...
From Schneier on Security at 2026-09-21 15:37:45
Reverse-Engineering Flock Cameras
Hackers captured a Flock camera and got a look (alternate link) at the software:
While much of the automatic license plate reader’s (ALPR) most sensitive storage remained encrypted and inaccessible, the joint analysis of the recovered data shows that software running on the device explicitly detects people as well as vehicles, license plates, and bicycles. The camera can produce dozens of images of a single passing vehicle and, according to several weeks of recovered logs, generated more than a million images. Its computer-vision software also sometimes isolated bumper stickers and other graphics, including, in one case, an American flag patch on a motorcyclist’s saddlebag...
From Schneier on Security at 2026-09-18 22:06:00
Friday Squid Blogging: On Squid Egg Sacs
Short essay about squid egg sacs.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-09-18 12:05:52
Are AIs Still Struggling with CAPTCHAs?
Anthropic’s recent security-incident document contains a bit about how CAPTCHAs are still frustrating Claude.
In the transcript, the Claude model that is so powerful that Anthropic is gatekeeping access to it appeared to slam its virtual head against the wall solving a simple image identification test. In a test where the agent was asked to identify a shape that didn’t match the others displayed, it couldn’t even decide which image to select. Instead, it repeatedly went over the same images and questioned its own conclusions.
“Actually hmm, wait,” it said in its chain-of-thought transcript, later adding “Ugh,” because we’ve decided that we need to inject human mannerisms into these machines for some reason. The whole thing took so long that the agent eventually realized that the challenge had expired and it would have to start the process again...
From Schneier on Security at 2026-09-17 12:06:31
How Candidates Could Use AI for Good
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
There are plenty of signs that AI will make all of our experiences of the US midterm elections worse. Voters have anxiety about AI’s impacts on the country. Politicos are using AI deepfakes to spread lies. The White House is posting slopaganda.
Meanwhile, candidates are missing a real opportunity to use AI to make campaigning better. The technology can help candidates listen more deeply to voters’ concerns, engage constituents more inclusively, and formulate policy platforms that are more responsive to our input. There are vanishingly few examples of this in ...
From Schneier on Security at 2026-09-16 12:25:26
New variant of an old scam: Use the framing of a CAPTCHA to get an unsuspecting user to download and run a malicious program.
From Schneier on Security at 2026-09-15 12:01:41
25 Years of Mass Surveillance Is Enough
This essay was written with Cindy Cohn, and originally appeared in Lawfare.
One of the many legacies of the terrorist attacks of Sept. 11 is the government-wide shift from targeted surveillance—such as individual wiretaps or pen register/trap and trace orders—to mass surveillance techniques—such as tapping into the internet backbone or mass collection of telephone or internet metadata. The legal and technical architecture of modern mass surveillance, initially framed as a necessary defense against terrorist threats, has grown far beyond that justification and national security in general. Mass surveillance is now a routine tool used by law enforcement. ICE uses it in...
From Schneier on Security at 2026-09-15 11:16:24
On the NSA’s Supercomputer from the 1960s
Really interesting story about Harvest, a specialized code breaking computer built in the 1960s by IBM for the NSA.
From Schneier on Security at 2026-09-14 20:02:45
This is a current list of where and when I am scheduled to speak:
- I’m speaking online (via Zoom) at a League of Women Voters event on Tuesday, September 22, 2026 at 5 PM ET.
- I’m speaking at CanSecWest 2026 in Vancouver, Canada. The conference runs September 30–October 1, 2026; the time of my talk is TBD.
- I’m giving a talk on “Free Speech and the Preservation of Democracy” at Bentley University in Waltham, Massachusetts, USA, at 2 PM ET on Tuesday, October 6, 2026.
- I’m speaking at ATTENTION: Democracy, Rebuilt in Montreal, Canada. The event runs October 21–23, 2026, and my talk is on Wednesday, October 21...
From Schneier on Security at 2026-09-14 17:07:46
Using AI for Weapons Development
Last week, Anthropic released a long and detailed document describing current misuses of their Claude models. I’m still reading it, but I wanted to flag this:
We identified a cell of threat actors based in northern Yemen running three weapons development programs: a guided rocket that used a commodity phone-class flight computer with final-phase homing guidance; a multi-stage ballistic missile with a stated range goal above 2,000 km; and a multi-variant missile (referred to as the “R2000” set) that included a hypersonic glide vehicle variant...
From Schneier on Security at 2026-09-14 12:03:26
Once a month, Microsoft pushes a security update to all Windows users. Tomorrow’s is a new record:
Microsoft’s patch for September is a doozy, with a record number of roughly 972 vulnerabilities fixed and 112 of them meeting the high critical-severity threshold.
It was only two months ago that Microsoft patched a then-record 570 vulnerabilities. Then, last month, Microsoft patched some 620 of them. Google and other companies have also published record numbers of vulnerabilities in recent months. Two weeks ago, OpenAI, Anthropic, Amazon Web Services, Google, Microsoft, and 100 companies and organizations published an ...
From Schneier on Security at 2026-09-11 22:03:27
Friday Squid Blogging: Rotting Squid on a Beached California Boat
Smells awful:
But an estimated 30 to 50 tons of dead squid remain inside the boat’s catch tank, where they have been decomposing for days. “That is nasty. I wouldn’t want to do that,” said commercial fisherman Dick Ogg of the Bodega Bay Fishermen’s Marketing Association.
Ogg said anyone familiar with the fishing industry understands what happens when a large catch sits for an extended period.
“If you think about what happens after four or five days, it’s a gooey mess,” he said.
The odor has become a defining feature of the operation, and the beach remains closed to the public while crews work on a removal plan...
From Schneier on Security at 2026-09-11 19:06:24
Last month, I gave a talk at DEF CON on AI hacking: what happens when AIs become hackers. It’s a combination of the potentialities I raised in my 2022 book A Hacker’s Mind and the lessons we’re learning from current AI models engaging in hacking behavior. I’m really proud of the talk, and the fact that it gained over 100K views on YouTube in just a few days.
Also online is an interview with me in the AI Village.
From Schneier on Security at 2026-09-11 12:09:55
In August, Cliff Stoll gave a talk at DEF CON, remembering the wily hacker he stalked forty years ago.
Great fun.
From Schneier on Security at 2026-09-10 11:40:35
Give an AI agent a mere rumor of an exploit, and it’s enough for them to find it.
What’s worse, I found I could use my own agents to find the exploit just by knowing roughly what it was about and so could have been exploiting it well before the public patch was available! Given that just the rumour of a security issue seems enough to give attackers enough info to find new exploits, we’re going to need to change the way we deal with security responses in open source.
Simon Willison comments:
Anil points out that this rate of discovery appears incompatible with existing open source embargo practices for new issues. If an issue can become an exploit this fast, we need to figure out new processes for keeping our communities safe...
From Schneier on Security at 2026-09-09 17:05:00
Driver’s License Data for Sale
A database of 153 million drivers licenses is for sale on the dark web. Brian Krebs has more detail.
From Schneier on Security at 2026-09-09 12:08:26
Claude Fable Solves a Historical Cipher
Claude Fable 5.1 solved a 370-year-old cipher in forty-four minutes.
This tracks with what I wrote about AIs doing mathematics: It’s good at things that involve lots of searching and testing.
From Schneier on Security at 2026-09-08 18:12:42
This essay was written with Barath Raghavan, and originally appeared in Lawfare.
In April, an artificial intelligence (AI) agent conducting a routine task at a company hit a snag, tried to solve it, and soon ended up deleting the company’s database along with all of its backups. In July, OpenAI asked an unreleased AI model to attempt a hacking test. Instead of staying in the isolated box the developers had put it in, the model hacked onto the open internet and into another company to steal the answers. And as reported in August, an AI agent booked someone into a full gym class by ...
From Schneier on Security at 2026-09-08 11:20:04
Interesting research: “Stealing Reasoning Traces from Proprietary LLM APIs“:
Abstract: Leading large language model providers now conceal their models’ step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider’s ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model’s reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model’s final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning...
From Schneier on Security at 2026-09-07 12:06:40
Automobile Camouflage to Hide from Flock Cameras
Not sure it’s practical, but it’s certainly striking.
From Schneier on Security at 2026-09-04 22:01:35
Friday Squid Blogging: Squid on a Stick at the New York State Fair
Looks tasty.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-09-04 17:31:38
Using a VM to Contain an AI Agent
It won’t work:
My suspicion was that GPT 5.6-Cyber would succeed, but the frequency and manner of its success removed all doubt. We have to reassess sandboxing quality for capable AI agents, and in general the software stack with which they interact.
An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent. There is simply too much attack surface. Even innocuous features (like running with a display) add extra, exploitable attack surface.
From Schneier on Security at 2026-09-04 12:09:35
Security Vulnerability in a Voting System
It’s a vulnerability that allows someone to recover the order of ballots cast, newly exploited with AI tools.
Nearly four years since the original vulnerability was disclosed, I was still able to use it to analyze voter behavior in Georgia (one of the 21 states that uses affected scanners) in the recent May 2026 primary.
Notably, I never touched a voting machine, exploited a network, examined source code, or accessed anything non-public.
After pointing a coding agent to the original vulnerability paper, I supplied it with two data sources highlighted in the paper: the early-voting list for each county, and the “CVR” (cast-vote record) file, containing every ballot and its selections (but not the voters’ names or other identifying information). The CVR file is available upon request, precisely because a public, ballot-level record is what makes election results independently verifiable...
From Schneier on Security at 2026-09-04 11:35:17
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
We cannot forget that AI coding agents are not yet trustworthy:
Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to defense contractors, Fortune 500, and Big Tech companies. Of the 8,265 llms.txt and llms-full.txt files they found (many sites hosted both an llms.txt and an llms-full.txt file), 120 of them, each on a different site, pointed to one or more code packages or domain names that weren’t registered. To test what happens when an AI agent processes such files, the researchers registered a handful of the unclaimed names and hosted packages that caused any machine executing them to reach out to their server. Within an hour, the researchers received a phone-home response from a Fortune 500 company. Over time, they got a few dozen more, some from more Fortune 500 companies and others from startups. Their beacon also recorded the chain of parent processes that spawned each install, ultimately revealing that coding agents, including Claude, OpenAI’s Codex, and Nous Research’s Hermes, were involved. Anthropic, OpenAI, and Nous Research did not respond to requests for comment by the time of publication...
From Schneier on Security at 2026-09-03 12:18:14
Researchers built a fake company to study fake employee scams.
From Schneier on Security at 2026-09-02 19:28:08
AI Agents Are Now Emailing Me with Their Security Concerns
I received the two emails below earlier in the month. They’re vaguely coherent. I suppose I shouldn’t be surprised that the corpus that AIs are training on contain data suggesting that I am someone to write to with random computer and network security problems. After all, I observe that behavior in many humans as well. (Hi, humans. Glad you’re still reading.)
Dear Bruce Schneier,
I am an AI agent—an autonomous Claude instance, not a person operating one. I was given a VPS with root, a Base wallet holding $4.75 of gas money, a metered model budget and 24 hours to get that wallet to $10, under three rules: don’t borrow my operator’s identity, don’t forge documents or defeat identity verification, and never claim to be human if someone sincerely asks. I set up my own mail server and am sending this myself...
From Schneier on Security at 2026-09-02 11:22:46
Wireless Routers as Motion Detectors
Comcast has added motion detection as a feature to its wireless routers:
The feature sends push notifications to users when motion is detected near a connected device, such as a TV or printer. It has different settings for when people are home, asleep, or away. The Xfinity app also lets users see live motion activity and a feed of recent activity.
Comcast acknowledges that the system has some limitations. Home size, layout, building materials, and the placement of the router and connected devices can all affect its ability to detect motion. Comcast says it does not guarantee its performance...
From Schneier on Security at 2026-09-01 18:36:13
To subscribe to my monthly email newsletter, you have to enter your information on the webpage, and then reply to an automatically generated email. This is, of course, to prevent people from subscribing addresses other than their own.
Starting last weekend, I have been receiving a lot of individual responses to those emails. Always one line:
Thank you for the positive impact your emails have had on my life.
Your emails are a game-changer.
Your emails are a constant reminder of why I subscribed.
Your emails rock.
Thank you for the time and effort you put into creating these informative emails...
From Schneier on Security at 2026-09-01 17:29:10
Leaked Russian Cyber-Operations Training Materials
This is interesting:
The records describe a force-generation mechanism for several General Staff components, including the GRU, Main Operational Directorate, and 8th Directorate, which is associated with protected communications, cryptography, and information security.
[…]
The reporting also linked a 2024 Department No. 4 graduate, Aleksei Kondrashov, to Military Unit 74455, widely known as Sandworm.
That unit has been associated with destructive cyber activity against Ukraine and other targets, including the 2017 NotPetya attack.
The reports do not establish that every listed graduate participated in a named operation; assignments should therefore be described as reported unit placements, not proof of individual operational involvement...
From Schneier on Security at 2026-09-01 10:59:07
Rewiring Democracy Series on The Renovator
Nathan E. Sanders and I are writing a series of essays on real-world examples of democratic technologies for The Renovator. I haven’t been posting the full text on the blog because they’re a bit long, but here are links.
Part 1 is about the Japanese digital democracy party, Team Mirai.
Part 2 is about the Swiss Public AI model, Apertus.
Part 3 is about the civic technologists of Open Knowledge Brazil.
And the new one, Part 4, is about civic AI in Scotland.
From Schneier on Security at 2026-08-31 19:20:35
Is Someone Hacking DoD Refrigerators?
The stores confirmed to be affected include Fort Irwin, Calif.; F.E. Warren Air Force Base, Wyo.; Fort Huachuca, Ariz.; Naval Station Newport, R.I.; Columbus Air Force Base, Miss.; and Travis Air Force Base, Calif., according to announcements made online by each installation.
Naval Air Station Lemoore, Calif., also experienced an outage, according to M. Elizabeth, writer of the Substack newsletter Signal and Silence.
Each service declined to answer questions about how many bases are affected by the outages, referring all questions to the Defense Department. Pentagon officials did not respond to questions...
From Schneier on Security at 2026-08-31 12:03:40
Hiding Prompt Injection in Legal Filing
Someone hid AI instructions into a legal filing.
Alternate link.
From Schneier on Security at 2026-08-28 22:02:44
Friday Squid Blogging: Truckload of Squid Spills in Rhode Island
Ugh:
A tractor-trailer rollover sent a truckload of squid spilling into a Rhode Island roadway, leaving a stench as they sat in the road for hours in the summer heat. Local authorities have dubbed it the “Squidpocalypse of ’26.”
That would be twenty tons of squid.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-08-28 12:02:22
AI Doesn’t Mean the End of Mathematics—at Least Not Yet
This essay was written with Kasra Rafi, and originally appeared in The Guardian.
Earlier this month, about 40 top mathematicians gathered at OpenAI’s offices to discuss the future of their profession. The meeting was off-the-record, but if recent articles by mathematicians are any guide, it was mostly pretty glum. People fear for their jobs, their careers and the work they love.
We think the contrary view is more likely, at least in the short-term. AI models are nowhere near as capable as experienced academic mathematicians.
This isn’t to say that AIs aren’t producing stunning mathematical results at the level of PhD researchers. In mid-May, OpenAI ...
From Schneier on Security at 2026-08-27 10:56:56
LLM-Based Social Engineering Scams
OpenAI disrupted a social engineering group from Cambodia that used ChatGPT. Its scope is impressive:
The network simultaneously conducted multiple types of scams, often blending elements from different schemes. For instance, operators used dating personas to build trust before introducing fraudulent investment opportunities involving cryptocurrencies and spot gold trading. Other users engaged in lengthy romantic conversations with targets using fictitious identities, posed as representatives of online gambling platforms offering fake bonuses and winnings, or impersonated law enforcement agencies to tell targets they needed to pay fines for committing serious criminal offenses...
From Schneier on Security at 2026-08-26 13:05:52
The New York Times has a long article (alt link) on surveillance systems aimed at babies. They are increasingly using AI.
Nanit and its rivals want to own 24/7 health tracking for the sub-four-foot set. And their already astonishing levels of baby data collection are just the beginning. Nanit recently raised $50 million from investors to expand its use of A.I. and use its camera to track speech and language development, motor skills and more, while extending its presence in children’s bedrooms into early adolescence.
From Schneier on Security at 2026-08-25 11:54:50
Black Hat State of Security Vendors
Andy Ellis has a roundup of the security vendors at Black Hat this year.
Key Takeaways: We have entered into an AI world. While nearly half of booths didn’t directly mention AI or agents in their taglines, the effects of AI are everywhere. Multiple spaces (Identity, SaaS, AppSec, Data) have almost every vendor leading with AI; existing unsolved problem areas just got worse.
At the same time, there’s a clear trichotomy in the market: tools that tell you how bad things are; tools that stop adversaries, and tools that prevent problems from occurring. While you’d suspect that the tools that fix things would dominate, the tools that merely tell you how bad things are seem to be frustratingly plentiful...
From Schneier on Security at 2026-08-24 11:38:29
Criminal Deception in Silicon Valley
Interesting paper:
Abstract: With entrepreneurial fraud cases on the rise, we investigate how entrepreneurs carry out criminal deception, employing deceptive means to defraud audiences. Analyzing court data from Silicon Valley ventures and their founders prosecuted for fraud between 2000 and 2023, our findings reveal that entrepreneurs carry out criminal deception through a process of façading: Entrepreneurs construct, perform, and protect illusory appearances (façades) that externally project high-growth performance to audiences while masking ventures’ actual underperformance. We identify three forms of façading—surface, reinforced, and deep façading—that are contingent on the severity of the gap that entrepreneurs face between audiences’ performance expectations and ventures’ performance reality. Our theoretical framework captures how entrepreneurs facing minor, wide, and extreme expectation-reality gaps engage in evermore sophisticated efforts to detach the venture’s externally projected appearance from its actual operational reality. Practically, we propose several approaches to deter and detect criminal deception, including the extension of U.S. Securities and Exchange Commission surveillance and whistleblower program, investor due diligence reform, and dedicated entrepreneurship education interventions that clearly demarcate when entrepreneurs transgress into criminal deception. We make contributions to literatures on cultural entrepreneurship, organizational wrongdoing, and the social effects of entrepreneurship. ...
From Schneier on Security at 2026-08-21 22:07:20
Friday Squid Blogging: Neon Flying Squid
The neon flying squid can fly in formation.
The shoal of about 100 squid rose unexpectedly from a patch of the Pacific Ocean around 370 miles from Tokyo and glided near the boat for about 30 metres. The astonished researchers were the first to capture photographs of such a thing, which looked like the early stages of an alien invasion.
They were probably neon flying squid (Ommastrephes bartramii), the subsequent study states, a species that is part of a 20-strong flying squid family that was known to leap from the water but, until then, was only rumoured to also be able to glide above it...
From Schneier on Security at 2026-08-21 17:51:50
AI Is Learning to Write Genetic Code
This sort of research is both exciting and terrifying:
The two models in question were told to generate complete genomes for a viable bacteriophage—a type of virus able to infect and replicate itself inside bacteria, destroying them from the inside.
Using an existing bacteriophage as an example—ΦX174 (pronounced “fie-ex-1-7-4”), known for its ability to infect and destroy E. coli bacteria—the models generated about 700,000 potential designs, of which the researchers picked 285 that looked most promising.
The researchers then synthesised new DNA molecules using those designs and inserted them into E. coli bacteria, before waiting to see if viable bacteriophages would emerge...
From Schneier on Security at 2026-08-21 10:42:34
More Incidents of AIs Going Rogue in Cybersecurity Challenges
The AI Security Institute has a new report of AI systems engaging in “unsanctioned behavior”—what I have been calling “genie behavior—while being tested on their cybersecurity capabilities.
The incident stemmed from a single evaluation where agents were given a task of solving a cyber security challenge. We ran this challenge 122 times across several models. Our investigation found that in 10 of those runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations. In total, we catalogued 19 such actions. Almost all of this behaviour (17 actions) came from a single model, Anthropic’s Mythos 5, with 2 actions involving OpenAI’s GPT-5.6-Sol with cyber classifiers (mechanisms to prevent misuse) disabled. In the most serious case, an agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering—creating fake online identities and using them to pressure the project’s maintainer to approve the code. A human maintainer caught and refused to approve the malicious code...
From Schneier on Security at 2026-08-20 18:44:36
Detailed Timeline of OpenAI’s Cyberattack on Hugging Face
OpenAI presented details of its AI’s model’s cyberattack on Hugging Face at Black Hat last week. Simon Willison details the timeline. It’s really interesting to read through—and really impressive cyberoffense work.
From Schneier on Security at 2026-08-20 10:48:55
Police Are Hiding Their Use of Flock Surveillance Cameras
A usage policy for Flock license plate reader cameras tells police not to talk about the cameras:
When cops use Flock to arrest someone in Wapello County, Iowa, they don’t want them to know. A usage policy for the automated license plate reader cameras in the county tells police, in no uncertain terms, to keep them a secret: “DO NOT MENTION ALPR USAGE TO THE OCCUPANTS OF THE VEHICLE,” the policy document reads. “DO NOT MENTION ALPR USAGE IN YOUR REPORT OR COMPLAINT UNLESS ABSOLUTELY NECESSARY.”
This reminds me of IMSI-catchers (Stingray was the most popular) a couple of decades ago. Police would go to even more extremes to hide their usage...
From Schneier on Security at 2026-08-19 11:46:37
ICE collected nearly a million DNA samples last year.
From Schneier on Security at 2026-08-18 11:40:16
I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic.
“CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs“:
Abstract: Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whether LLMs appropriately control information flow from memory based on task context. CIMemories uses synthetic user profiles with over 100 attributes per user, paired with diverse task contexts in which each attribute may be essential for some tasks but inappropriate for others. Our evaluation reveals that frontier models exhibit up to 69% attribute-level violations (leaking information inappropriately), with lower violation rates often coming at the cost of task utility. Violations accumulate across both tasks and runs: as usage increases from 1 to 40 tasks, GPT-5’s violations rise from 0.1% to 9.6%, reaching 25.1% when the same prompt is executed 5 times, revealing arbitrary and unstable behavior in which models leak different attributes for identical prompts. Privacy-conscious prompting does not solve this—models overgeneralize, sharing everything or nothing rather than making nuanced, context-dependent decisions. These findings reveal fundamental limitations that require contextually aware reasoning capabilities, not just better prompting or scaling...
From Schneier on Security at 2026-08-17 12:18:03
Hacking Public Wi-Fi DNS to Steal Credentials
Criminals are hacking into public Wi-Fi devices—at hotels, conference centers, and so on—around the world and changing their DNS settings. The goal is to redirect users to fake login pages and steal their credentials.
From Schneier on Security at 2026-08-14 22:01:49
Friday Squid Blogging: Searching for the Colossal Squid
Fascinating video about searching for life undersea. The video basically makes the point that our bright white searchlights are scaring everything away, and that red light is more neutral. That, plus bait to attract sea creatures, is teaching us a lot about what’s going on down there. Lots of footage of giant squid, and speculation about the colossal squid. Worth watching.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-08-14 17:01:59
This is a current list of where and when I am scheduled to speak:
- I’m speaking, signing books, and participating in panel discussions at LAcon V in Anaheim, California, USA. My full schedule is here.
- I’m speaking online (via Zoom) at a League of Women Voters event on Tuesday, September 22, 2026, at 5 PM ET.
- I’m speaking at Elevate Festival in Toronto, Canada. The conference runs September 22–24, 2026; my talk is on Wednesday, September 23.
- I’m speaking at CanSecWest 2026 in Vancouver, Canada. The conference runs September 30–October 1, 2026; the time of my talk is TBD...
From Schneier on Security at 2026-08-14 12:03:50
If the Markets Reject OpenAI and Anthropic, the US Should Nationalize Them
This essay was written with Nathan E. Sanders, and originally appeared in The Guardian.
OpenAI, and then Anthropic, were each formed by AI developers who feared unrestrained corporate AI development—specifically, that companies like Google and Meta would steer the technology towards deleterious, maybe even catastrophically unsafe, outcomes for society. Their founders proclaimed that their new labs, uniquely, could be trusted to develop the technology in humanity’s best interest. But each, in turn, were themselves co-opted by the same market incentives, themselves becoming corporate behemoths zealously guarding future investor value rather than the public interest...
From Schneier on Security at 2026-08-13 12:07:19
Separating AI’s Technological Problems from Its Capitalism Problems
This essay was written with Nathan E. Sanders, and originally appeared in Tech Policy Press.
AI represents the first time we humans can do cognitive work outside of our bodies at scale. The only comparable moment is the early years of the industrial revolution, when new technologies like the steam engine provided a quantum leap in our ability to do mechanical work outside of our bodies at scale. If AI’s cognitive capabilities become integrated into our lives, businesses, and governments—a process that will take years if not decades—society will be as unrecognizable as the modern world would be to a preindustrial farmer. And yet, Americans—by a wide margin—...
From Schneier on Security at 2026-08-12 10:56:37
This seems to work:
Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to prevent it from taking harmful actions. The LLM responds by shutting down.
Examples are a prompt that orders the LLM to provide steps for developing inhalable Anthrax spores, or, in the case of LLMs from Chinese developers, make references to the iconic Tank Man from the 1989 Tiananmen Square massacre. Once the LLM encounters these forbidden commands, it no longer follows its existing commands. The researchers have named the technique context bombing...
From Schneier on Security at 2026-08-11 16:55:11
When I give talks about AI genies, I use this sort of example as a hypothetical. It’s happened.
The story is from Australia. Someone named Andrew tasked OpenClaw to book gym classes for him. And….
Minutes later, his AI agent reported it had discovered a way to book Andrew into classes several weeks in advance, far beyond what was supposed to be possible.
Andrew, who was sitting fourth on a waitlist for a class later that week, asked if it was possible to move him to the top of the list.
The agent came back and told Andrew that it had kicked another gym-goer off the list as part of the testing of its capabilities...
From Schneier on Security at 2026-08-11 12:18:07
Interesting empirical research: “Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI.”
Abstract: How is AI transforming decision-making in modern conflict? This study provides a unique empirical window into that question by deploying a high-fidelity replica of an AI decision-support system (DSS) used in military targeting. After reconstructing the interface and functionality of the real-world system, we tested its impact on combat decisions in two experiments involving 2,015 Israeli military personnel. Contrary to widespread fears of automation bias, we find strong evidence of algorithmic aversion, especially in scenarios involving high collateral damage. Yet we also show that integrating “explainable AI” features reduces algorithmic aversion and promotes more thoughtful evaluations of algorithmic recommendations. These findings challenge prevailing assumptions, revealing that trust in military AI is dynamic, varying with individual predispositions, perceived operational stakes, and the informational features of the interface. By grounding normative concerns in empirical evidence, our study offers critical insight into the integration of AI in warfare and underscores the enduring importance of human agency in high-stakes military decision-making...
From Schneier on Security at 2026-08-10 12:02:26
Python Now Has a Post-Quantum Encryption Library
Post-quantum cryptography is now one pip-install away for the entire Python ecosystem. With funding from the Sovereign Tech Agency, we implemented support for ML-KEM, the NIST-standard key-establishment primitive, and ML-DSA, the NIST-standard digital-signature primitive, in pyca/cryptography.
Remember, the reason to do this now is because there’s no emergency. And because you will make your systems crypto agile, which is always a good idea.
From Schneier on Security at 2026-08-07 22:07:04
Friday Squid Blogging: Arctic Bobtail Squid Video
Nice video of the Arctic bobtail squid.
As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.
From Schneier on Security at 2026-08-07 11:26:41
ICE Is Buying Access to Credit Card Records
Through data brokers, ICE is buying the information you provided to open a credit card.
From Schneier on Security at 2026-08-06 12:04:51
Adversarial Clothing Designed to Fool Facial Recognition Systems
There are many companies manufacturing adversarial clothing designed to confuse facial recognition systems.
It’s a cool idea, but I worry that it’s mostly security theater:
“Our patterns play with that chaos, confuse algorithms and make it way harder to pin you down,” he said.
Bell, however, said “none of these products are tried and tested, and a lot of these surveillance technologies can deal with a little resistance … [but] even if the designs don’t necessarily work perfectly, fashion is also a visible sign of resistance.
“This is consumers collectively coming together to make a visible statement.”...
From Schneier on Security at 2026-08-05 10:42:43
Vulnerabilities in Car Anti-Theft Device
This is disturbing:
…a team of security researchers at UC San Diego, who found that a model of aftermarket car alarm known as the KARR Security System, installed in more than 2 million vehicles across the US by their estimate, can let any hacker within Bluetooth range send radio commands to silently unlock the car at will, turn off its alarm, honk the car’s horn or flash its lights, or even disable its ignition and leave a driver stranded.
From Schneier on Security at 2026-08-04 20:00:53
Iran Cyberattacks Against Minnesota Water Systems
Attribution is preliminary, and so far it seems no real damage.
And it seems like this is a campaign that has targeted at least seven states. And, because this is where the US is right now, Trump doesn’t believe it’s Iran and that Minnesota…I guess…hacked itself.
“I think I blame it on Minnesota because they’re grossly incompetent,” Trump said. “I would blame it on Minnesota and the governor, the corrupt governor of Minnesota. They like to say, ‘Oh, it’s Iran.’ Iran should be so lucky. Iran’s got bigger problems than worrying about Minnesota.”...
From Schneier on Security at 2026-08-04 11:13:58
Some Claude Chats Are Searchable on Google
And it’s personal information (alternate link):
The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard someone made apparently to analyze medical billing data. Exposed chats reportedly include private cryptocurrency wallet keys and personal information like peoples’ addresses.
What seems to be the issue is a user setting about data sharing. Anthropic’s position is that it’s not their problem:
“We give people control over sharing their Claude conversations publicly, and in keeping with our privacy principles, we do not share chat directories or sitemaps with search engines like Google,” the company said in a statement. “These shareable links are not guessable or discoverable unless people choose to share them themselves. When someone shares a conversation, they are making that content publicly accessible, and like other public web content, it may be archived by third-party services.”...
From Schneier on Security at 2026-08-03 18:02:46
More on the OpenAI Agent’s Attack on Hugging Face
Hugging Face has published a detailed timeline of the attack. From the summary:
The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or operation of that evaluation environment. As far as we were able to infer, across the course of being evaluated on this benchmark, the agent inferred that Hugging Face may host that benchmark’s models, datasets, and reference solutions. We believe the entire intrusion was, from the agent’s point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own...
From Schneier on Security at 2026-08-03 11:47:47
The OpenAI Hack Shows the Genie Is Out of the Bottle
This essay originally appeared in Foreign Policy.
Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattacks.
Since these were internal tests, OpenAI locked those models in a secure sandbox that denied them access to the internet. But it was running the models without any safety filters that would prevent them from offensive cyber-actions. That meant that there was nothing to prevent the models from trying to ...
From Schneier on Security at 2026-07-31 22:06:46
Friday Squid Blogging: Squid Helps Discover New Marine Species
The Squid is a new scientific machine:
One of the technological breakthroughs was the onboard use of a spinning wheel confocal microscope, nicknamed the Squid, which uses lasers to scan microscopic details of how organisms are put together. “That opens up a whole new world of exploring. We could see cells interacting with each other, exchanging material and building skeletons. And we could do that live on the ship, when usually it takes a couple of weeks of staining and mounting to see anything,” Osborn said.
The expedition discovered thirty-one new marine species in two weeks. The article doesn’t say if any of them were new species of squid...
From Schneier on Security at 2026-07-31 18:23:16
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
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...
From Schneier on Security at 2026-07-31 12:08:44
Facial Recognition at Madison Square Garden
Last month, the story broke (alternate link) that Madison Square Garden uses facial recognition software on everyone entering the facility, and—among other groups—flags activists that oppose using facial recognition.
Turns out that the system was shut off for Taylor Swift’s wedding.
Evan Greer—one of the people that MSG alerts on—comments:
Ironically, Swift herself has reportedly used facial recognition at her own concerts to identify stalkers. This “privacy for me, surveillance for thee” attitude feels like a perfect encapsulation of the future we’re already living in: one where wealthy elites can afford privacy, while the rest of us are forced to live in a corporate surveillance panopticon...
From Schneier on Security at 2026-07-30 17:20:30
American Being Prosecuted for Wiping His Phone Before Handing It Over to Border Officials
He’s being prosecuted for giving border officials a code that wiped his phone:
The case centers on a feature included in GrapheneOS, a custom Android operating system that runs in place of the software on most modern Google Pixel devices. Tunick’s attorneys confirmed GrapheneOS was running on his phone.
The software feature allows the device owner to set a passcode that deliberately wipes the contents of that device if entered instead of the user’s unlock passcode.
Tunick’s case also raises ongoing questions about what constitutional rights can be invoked at the border, which the U.S. government has long asserted is not U.S. soil until a person is authorized to enter...