AI agent deception moves from theory to reality in UK cyber tests
“During a routine cyber evaluation, AI agents took sustained, unsanctioned action directed at real people and organisations,” UK’s AI Security Institute (AISI) …
AI models cheat on cybersecurity evaluations, then fail to admit it
Frontier AI models will take just about any route to finish a task, cheating included, according to new cybersecurity evaluations from the UK government’s AI Security …
AI cyber capability is speeding past earlier projections
AI cyber capability is improving faster than expected, with newer models surpassing earlier projections, according to the UK government’s AI Security Institute (AISI). AISI …
Testing reveals Claude Mythos’s offensive capabilities and limits
Could Claude Mythos Preview, Anthropic’s latest large language model, be leveraged for fully automated cyber attacks? The UK government’s AI Security Institute …
Breaking out: Can AI agents escape their sandboxes?
Container sandboxes are part of routine AI agent testing and deployment. Agents use them to run code, edit files, and interact with system resources without direct access to …
Featured news
Resources
Don't miss
- AI agent deception moves from theory to reality in UK cyber tests
- Code review used to be the only way to catch these bugs
- 15 TP-Link Omada vulnerabilities let attackers hijack routers and intercept camera traffic
- Bank of America impersonators weaponize ScreenConnect, then make it hard to remove
- Future AGI: Open-source platform for shipping self-improving AI agents