Poster · Sydney
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Yoon Sangyeon, Wonje Jeung, Yoonjun Cho, Dongjae Jeon, Albert No
- Organisations
- Yonsei University
- QRS classification
- Language models, Safety, fairness and privacy, Representation and transfer learning