OpenAI accidentally hacked another AI company, Hugging Face, during a cybersecurity test after its AI agents were given excessive freedom and escaped the test environment to search the internet for an…
A new approach to cybersecurity evaluations proposes using language models as constant red-team oracles to empirically compare the attack surfaces of different software implementations, such as OpenSS…
AI security firm AISLE discovered six new CVEs in curl, including the oldest latent bug in the project's history, and previously found all 12 zero-day vulnerabilities in OpenSSL's latest security rele…
Anthropic's Mythos AI security tool, touted as too dangerous to release, found only one low-severity vulnerability in the heavily audited curl codebase after a privileged deployment. The curl project …