Malicious LiteLLM PyPI releases stole cloud and SSH keys, Kubernetes tokens, and other secrets, potentially exposing 2,500+ ...
Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...
Security researcher Kevin Beaumont got a call last week from a major US technology company that insisted it had nothing to worry about: all the credentials stolen in March's LiteLLM supply chain ...
CISA warns that three vulnerabilities in IBM Langflow OSS, N-able N-central, and Apache Tomcat have been exploited in the ...
The March 2026 LiteLLM supply chain attack likely affected over 2,500 organizations and exposed over 430,000 CI/CD pipelines.
An evil twin attack on a Delta flight, the LiteLLM attack exposed 430,000 pipelines, Russian hackers targeted Ukrainian IT ...
The AI lab said the models engaged in a "multiagent turf war" during a testing session.
Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit found three incidents “in which a model accessed the internet from within ...
When the Benevolent Bureau of Birds runs the DEF CON Capture the Flag finals this weekend, they will be presiding over something that did not exist two years ago: a competitive environment where ...
Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...
OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.
The disclosure follows a review of 141 006 evaluation runs, which uncovered three incidents where Claude models reached the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results