Poster · Paris
Gradient-Guided Smoothing for LLM Safety Defense
- When
- Wed 9 Dec 2026, 17:00–19:00 CET
- Where
- Paris Poster Hall
- Session
- Paris Poster Session 2
- Authors
- Yuxuan Gu, Xiaocheng Feng, kun Zhu, Lunjun Liu, Zhihao Yao, Lei Huang, Weihong Zhong, Bing Qin
- Organisations
- Harbin Institute of Technology, Harbin Engineering University
- QRS classification
- Language models, Safety, fairness and privacy