Poster · Sydney
SelfGuard: Self-Supervised Deviation Modeling for Multi-Modal Jailbreak Detection
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Chenchen Jing, Hongli Guo, Huarong Jia, TianweiBai, Che Sun, Yang Liu, Chunhua Shen
- Organisations
- Zhejiang University of Technology, Beijing Institute of Technology, Liaoning Technical University, Shenzhen MSU-BIT University, Zhejiang University, University of Adelaide
- QRS classification
- Safety, fairness and privacy, Representation and transfer learning