Poster · Atlanta
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
- When
- Thu 10 Dec 2026, 16:30–19:30 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 4
- Authors
- Xinkai Zhang, Zhipeng Wei, Huanli Gong, Jing Ting Zheng, Yuchen Zhang, Yue Dong, N. Benjamin Erichson
- Organisations
- University of California, Berkeley, University of California, Riverside, Lawrence Berkeley National Laboratory
- QRS classification
- Language models, Safety, fairness and privacy