Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- ICML 2025
Conference paper
Publications
2 results for Yuguang Yao
Visual Prompting for Adversarial Robustness
- Aochuan Chen
- Peter Lorenz
- et al.
- 2022
- NeurIPS 2022
Workshop paper