A comment:

3% of ‘critical’ software security bugs, in all of recorded history, have been found in the last month. This is on pace to find another ~100,000 bugs this year alone, adding ~26% more vulnerabilities to the all time total Do you realize how fucking insane that is?

Yes. It is a new world out there.

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.

Blog moderation policy.

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...

Researchers set up a fake start-up company to study fraudulent North Korean IT workers.

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...

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. ...

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.

Blog moderation policy.

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...

PHP maintainers have released fixes for 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...

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.

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...

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...

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.

Blog moderation policy.

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...

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...

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...

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.

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...

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.

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.