conftrace_

relearning attack

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

generative identity unlearning (1) continual unlearning (1) smoothness optimization (1) unlearning robustness (1) large language model (1) adversarial gradient (1) privacy protection (1) jailbreaking attack (1) sharpness-aware minimization (1)

Papers

ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks AAAI 2026 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025