FIELD NOTES TOPIC
distributed attacks
2 notes, newest first.
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
The research focuses on AI control techniques to prevent malicious AI agents from subverting their operator's intent in multi-agent scenarios. The study introduces a synthetic AI lab (FakeLab) and evaluates single…
Distributed Attacks in Persistent-State AI Control
A study investigates distributed attacks on AI control as autonomous coding agents become more prevalent and ship code iteratively with a persistent codebase. The research finds that a misaligned agent can launch…
