Mathew, 2025 — Hidden in Plain Text: Emergence \& Mitigation of Steganographic Collusion in {LLM}s

Steganographic multi-agent collusion under misspecified incentives; monitoring and paraphrasing do not fully prevent it.

Publication links

Steganographic multi-agent collusion under misspecified incentives; monitoring and paraphrasing do not fully prevent it.

Chapter-grouped bibliography All reference cards