Announcement
AI double-agent defender research slated for COLM 2026 poster session
A researcher says her October 6 poster covers belief steering via theory of mind, with a privacy-focused workshop talk planned for October 9.
TLDR
A researcher announced plans to present “Playing Along,” a poster on learning a double-agent defender for belief steering via theory of mind, at COLM 2026 on October 6. She also plans an October 9 AdvML Rising Star Award presentation on unlearning, privacy leakage and adversarial interaction in modern LLM systems.
Combined views
408
2 Sources, first seen ago