Image de couverture de livre

Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rezkellah, Fatmazohra, Dakhmouche, Ramzi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language Cryptography and Security Computers and Society Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
par: Zhang, Yihao, et autres
Publié: (2024)

Exploring the Robustness of In-Context Learning with Noisy Labels
par: Cheng, Chen, et autres
Publié: (2024)

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
par: Allouah, Youssef, et autres
Publié: (2024)

Secure LLM Fine-Tuning via Safety-Aware Probing
par: Wu, Chengcan, et autres
Publié: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
par: Zhang, Zhixin, et autres
Publié: (2025)

Boosting Jailbreak Attack with Momentum
par: Zhang, Yihao, et autres
Publié: (2024)

RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
par: Wei, Zeming, et autres
Publié: (2026)

UCD: Unlearning in LLMs via Contrastive Decoding
par: Suriyakumar, Vinith M., et autres
Publié: (2025)

An Adversarial Perspective on Machine Unlearning for AI Safety
par: Łucki, Jakub, et autres
Publié: (2024)

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
par: Li, Na, et autres
Publié: (2024)

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
par: Xu, Xiaoyu, et autres
Publié: (2025)

Differential Privacy via Distributionally Robust Optimization
par: Selvi, Aras, et autres
Publié: (2023)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
par: Yuan, Hongbang, et autres
Publié: (2024)

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
par: Chen, Yen-Shan, et autres
Publié: (2026)

GSE: Group-wise Sparse and Explainable Adversarial Attacks
par: Sadiku, Shpresim, et autres
Publié: (2023)

Efficient Optimization Algorithms for Linear Adversarial Training
par: RIbeiro, Antônio H., et autres
Publié: (2024)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
par: Li, Nathaniel, et autres
Publié: (2024)

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
par: Jang, Yeonwoo, et autres
Publié: (2025)

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
par: Ribeiro, Antônio H., et autres
Publié: (2025)

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
par: Hou, Abe Bohan, et autres
Publié: (2024)

SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models
par: Dabiriaghdam, Amirhossein, et autres
Publié: (2025)

Second-Order Min-Max Optimization with Lazy Hessians
par: Chen, Lesi, et autres
Publié: (2024)

SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
par: Sun, Jialong, et autres
Publié: (2026)

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
par: Xu, Xiaoyu, et autres
Publié: (2025)

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
par: Islamov, Rustem, et autres
Publié: (2026)

Machine Unlearning Fails to Remove Data Poisoning Attacks
par: Pawelczyk, Martin, et autres
Publié: (2024)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
par: Zhu, Kaijie, et autres
Publié: (2023)

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
par: Brown, Hannah, et autres
Publié: (2024)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
par: Di, Jimmy Z., et autres
Publié: (2022)

Identifying and Understanding Cross-Class Features in Adversarial Training
par: Wei, Zeming, et autres
Publié: (2025)

SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models
par: Djuhera, Aladin, et autres
Publié: (2025)

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
par: Xue, Jiaqi, et autres
Publié: (2024)

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
par: An, Bang, et autres
Publié: (2024)

In the Name of Fairness: Assessing the Bias in Clinical Record De-identification
par: Xiao, Yuxin, et autres
Publié: (2023)

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
par: Li, Ran, et autres
Publié: (2025)

Learning Fair Robustness via Domain Mixup
par: Zhong, Meiyu, et autres
Publié: (2024)

LLM Unlearning Should Be Form-Independent
par: Ye, Xiaotian, et autres
Publié: (2025)

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
par: Muhamed, Aashiq, et autres
Publié: (2025)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
par: Kaneko, Masahiro, et autres
Publié: (2025)

Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks
par: Wang, Rui, et autres
Publié: (2025)