Malicious LiteLLM PyPI releases stole cloud and SSH keys, Kubernetes tokens, and other secrets, potentially exposing 2,500+ ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent that attacked Hugging Face also exploited a customer's unsecured endpoint.

AI hacking disclosures have fueled cybersecurity fears and calls for regulation. They're also the best marketing tool any lab ...

CISA warns that three vulnerabilities in IBM Langflow OSS, N-able N-central, and Apache Tomcat have been exploited in the ...

Vulnerabilities can lurk within production code for years or decades — and AI tools have opened a gateway to a glut of new long-hidden discoveries. In 2021, a vulnerability was revealed in a system ...

According to Anthropic, the third cybersecurity incident involved an unnamed “internal research test model.” It compromised ...

Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...

Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed ...

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 ...