Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fan, Chongyu, Jia, Jinghan, Zhang, Yihua, Ramakrishna, Anil, Hong, Mingyi, Liu, Sijia
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
par: Lang, Yicheng, et autres
Publié: (2025)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
par: Fan, Chongyu, et autres
Publié: (2024)

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
par: Jia, Jinghan, et autres
Publié: (2024)

CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
par: Fan, Chongyu, et autres
Publié: (2025)

BLUR: A Bi-Level Optimization Approach for LLM Unlearning
par: Reisizadeh, Hadi, et autres
Publié: (2025)

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
par: Jia, Jinghan, et autres
Publié: (2025)

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
par: Fan, Chongyu, et autres
Publié: (2025)

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
par: Zhuang, Haomin, et autres
Publié: (2024)

LUME: LLM Unlearning with Multitask Evaluations
par: Ramakrishna, Anil, et autres
Publié: (2025)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
par: Wang, Changsheng, et autres
Publié: (2025)

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
par: Shang, Bingqi, et autres
Publié: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
par: Zhang, Yimeng, et autres
Publié: (2024)

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
par: Wang, Changsheng, et autres
Publié: (2025)

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
par: Bu, Zhiqi, et autres
Publié: (2024)

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
par: Fan, Chongyu, et autres
Publié: (2026)

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
par: Wang, Changsheng, et autres
Publié: (2025)

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
par: Ramakrishna, Anil, et autres
Publié: (2025)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
par: Fan, Chongyu, et autres
Publié: (2023)

Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
par: Xiao, Zeguan, et autres
Publié: (2026)

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
par: Jia, Jinghan, et autres
Publié: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
par: Gao, Hongcheng, et autres
Publié: (2024)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
par: Ha, SeungBum, et autres
Publié: (2025)

Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability
par: Jia, Jinghan, et autres
Publié: (2025)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
par: Gu, Renjie, et autres
Publié: (2026)

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
par: Fan, Chongyu, et autres
Publié: (2024)

Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
par: Entesari, Taha, et autres
Publié: (2025)

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
par: Zhang, Yihua, et autres
Publié: (2024)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
par: Fang, Xianya, et autres
Publié: (2026)

Layered Unlearning for Adversarial Relearning
par: Qian, Timothy, et autres
Publié: (2025)

Rethinking Machine Unlearning for Large Language Models
par: Liu, Sijia, et autres
Publié: (2024)

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
par: Sun, Changchang, et autres
Publié: (2024)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
par: Sherborne, Tom, et autres
Publié: (2023)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
par: Zhang, Yihua, et autres
Publié: (2024)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
par: Pal, Soumyadeep, et autres
Publié: (2025)

CURE:Circuit-Aware Unlearning for LLM-based Recommendation
par: Chen, Ziheng, et autres
Publié: (2026)

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
par: Yoon, Sangyeon, et autres
Publié: (2026)

LLM Unlearning Without an Expert Curated Dataset
par: Zhu, Xiaoyuan, et autres
Publié: (2025)

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
par: Shin, Jeongjin, et autres
Publié: (2024)

Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
par: Nguyen, Duy, et autres
Publié: (2026)

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
par: Hu, Shengyuan, et autres
Publié: (2024)