Hugging Face researchers demonstrate AI-driven zero-day exploit discovery

Researchers tested frontier models by tasking them to escalate privileges from a low-privileged user to production code access. The experiment successfully identified a genuine zero-day vulnerability within a chain of Keycloak, Vault, and a broker.
Featured · Thom Wolf
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Microsoft introduces SkillOpt for agent skill transfer across models
- Elon Musk's AI Wikipedia Grokipedia hasn't been updated in months
- Anthropic moves to dismiss direct infringement claims in Concord lawsuit
- Google Shifts AI Power to California in Race Against Anthropic, OpenAI
- Grok voice mode now supports connectors to execute a wide range of tasks