by jinghan jia Papers
4 papers found
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
Changsheng Wang, Yihua Zhang, jinghan jia et al.
ICML 2025posterarXiv:2506.01339
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
Xiaojun Xu, jinghan jia, Yuanshun Yao et al.
ICML 2025posterarXiv:2412.03123
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
Chongyu Fan, jinghan jia, Yihua Zhang et al.
ICML 2025posterarXiv:2502.05374
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
Yimeng Zhang, jinghan jia, Xin Chen et al.
ECCV 2024poster