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 [...]
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 [...]
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 im [...]
Born out of academia and raised in corporate IT departments, the Security Assertion Markup Language (SAML) authentication protocol continues to be a staple in these organizations. However, it’s time for it to retire. With the rise of software-as-a-service (SaaS) companies in the late aughts, IT departments needed a way for users to authenticate to many new web services. SAML and the burgeoni [...]
When the push came to start weaving AI into our everyday work, I had doubts at the start. But I have since come around, and here's why. What I actually do (and why that matters) I'm on the engineering team at Intigriti, but my role is Quality Assurance (QA), so I'm the one writing the tests, running the tests, and then collaborating with the developers when something doesn't work the way it shoul [...]
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. Blog moderation policy. [...]
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 [...]
Security firms have published numerous blog posts describing how they pointed their agent harness at a codebase and found dozens of bugs (we’re one of them). However, these posts tend to focus on agentic code review, which is just one aspect of how we use AI in our security reviews. We want to give a different perspective: before code review even starts, agents now allow us to build custom tooling [...]
In this post, we examine two vibe-coded credential harvesting platforms, Loot and UltraVault, and the Amazon Bedrock abuse used to validate stolen secrets. [...]
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 A [...]
The consumer data broker Radaris.com has long had a reputation for ignoring requests to remove personal information from its vast empire of people-search services online. That reputation caught up with the company recently in a lawsuit alleging Radaris violated a New Jersey privacy law that provides for hefty fines against data brokers that publish personal information on state law enforcement off [...]
New variant of an old scam: Use the framing of a CAPTCHA to get an unsuspecting user to download and run a malicious program. [...]
In this post, we walk through different threats to GitHub and how to detect them. [...]
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 met [...]
1Password’s FLAWED report, published on August 6, 2026, gives defenders a misleading picture of AI patching. Its headline says models produced clean fixes only 26% of the time. That figure includes experiments that deliberately instructed agents to apply the wrong fix, along with experiments in which agents could not compile or test their patches. The report risks making defenders less effective b [...]
Really interesting story about Harvest, a specialized code breaking computer built in the 1960s by IBM for the NSA. [...]
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 [...]
Here's the uncomfortable part first: in August 2026, researchers found AI agents connected to Hugging Face running loose inside enterprise networks. No owner, no audit trail, nobody who could tell you they existed until something broke. If that sentence made your stomach drop a little, good, because it should. It's the same blind spot most security teams are sitting on right now. They just haven' [...]
Fermat famously claimed to have a “truly marvelous proof” of his Last Theorem, but he never wrote it down, insisting the margin of his page was too narrow to contain it. A few centuries later, Anthropic announced a complete formalization of Fermat’s Last Theorem using 13 million lines of Lean code (clearly not what Fermat intended). Luckily, we found a wonderfully cursed Lean bug, shown belo [...]
Microsoft Corp. today issued updates to plug at least 974 security holes in its Windows operating systems and other software, by far its biggest single patch batch ever. Microsoft says artificial intelligence is helping to speed the discovery of vulnerabilities, but security experts warn that many organizations already are struggling to prioritize the more human-intensive endeavor of testing and d [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973143 [...]
MariaDB disclosed a bug submitted by byteoverride: https://hackerone.com/reports/3788482 [...]
MariaDB disclosed a bug submitted by pinebudweiser: https://hackerone.com/reports/3897914 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973194 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3971518 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973111 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3993850 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3993973 [...]
When I wake up in the morning, as a Senior Software Engineer at Intigriti, the first thing I do is make coffee. The second thing I do is pick up exactly where I left off the day before, usually mid-conversation with an AI. That probably sounds a bit strange. And, depending on who you're asking, maybe a little unsettling too. But that's genuinely what my working day looks like now, and I think it' [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973213 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973219 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3972293 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3971706 [...]
curl disclosed a bug submitted by giant_anteater: https://hackerone.com/reports/3973121 [...]
MariaDB disclosed a bug submitted by kevin_mizu: https://hackerone.com/reports/3876430 [...]
MariaDB disclosed a bug submitted by v3rtical: https://hackerone.com/reports/3909248 [...]
MariaDB disclosed a bug submitted by dogeshark: https://hackerone.com/reports/3897588 [...]
MariaDB disclosed a bug submitted by dogeshark: https://hackerone.com/reports/3889667 [...]
Nextcloud disclosed a bug submitted by chinnuy935336: https://hackerone.com/reports/3513471 - Bounty: $150 [...]
Nextcloud disclosed a bug submitted by cybershinu90: https://hackerone.com/reports/3507273 - Bounty: $100 [...]
Nextcloud disclosed a bug submitted by nishantbaswal1996: https://hackerone.com/reports/3521639 [...]
Nextcloud disclosed a bug submitted by charankumar39: https://hackerone.com/reports/3521646 [...]
Nextcloud disclosed a bug submitted by cyebrsunita: https://hackerone.com/reports/3534050 - Bounty: $150 [...]
Nextcloud disclosed a bug submitted by njh215: https://hackerone.com/reports/3617729 [...]