Skip to content
conftrace_
2025 ICML ICML 2025

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Optimization Artificial Intelligence > Core AI > Large Language Models

Keywords

sharpness-aware minimization jailbreaking attack large language model relearning attack smoothness optimization unlearning robustness
Download PDF