Interesting research: “ AI Models Can Provably Hide Arbitrary Capabilities ” Abstract: Capability evaluations aim to surface dangerous model behaviors…
Tag: Schneier on Security
Studying Fraudulent North Korean IT Workers
Researchers set up a fake start-up company to study fraudulent North Korean IT workers.
Bias in Qwen3-Coder Model
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,…
Hiding Capabilities in AI Models
Interesting research: “ AI Models Can Provably Hide Arbitrary Capabilities ” Abstract: Capability evaluations aim to surface dangerous model behaviors…
Bias in Qwen3-Coder Model
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,…
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…
New Serious PHP Vulnerabilities Released and Patched
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…
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…
Compromised TLS Certificates
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
Upcoming Speaking Engagements
This is a current list of where and when I am scheduled to speak: I’m speaking at ATTENTION: Democracy, Rebuilt in Montreal, Quebec, Canada. The event…
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…