Preprint
Aug 2026
PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies
PsychJail is presented, a psychology-guided framework for red teaming aligned LLMs through theory-grounded, multi-turn persuasion and establishes psychological jailbreaks as a distinct red-teaming frontier for increasingly interactive LLMs.
Ze-Yu Feng, Qing-Yuan Wu, Yu-Zhe Luo et al.
· 1 citation