Poster · Sydney
TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
- When
- Thu 10 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 6
- Authors
- Hongyi Li, Yufei Wang, Chengxuan Zhou, Qinlin Xie, Yanting Chen, Jiawei Ye, Wu Jie
- Organisations
- Fudan University
- QRS classification
- Language models, Safety, fairness and privacy