Copertina

Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rezkellah, Fatmazohra, Dakhmouche, Ramzi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computation and Language Cryptography and Security Computers and Society Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Exploring the Robustness of In-Context Learning with Noisy Labels
di: Cheng, Chen, et al.
Pubblicazione: (2024)

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
di: Allouah, Youssef, et al.
Pubblicazione: (2024)

Secure LLM Fine-Tuning via Safety-Aware Probing
di: Wu, Chengcan, et al.
Pubblicazione: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
di: Zhang, Zhixin, et al.
Pubblicazione: (2025)

Boosting Jailbreak Attack with Momentum
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
di: Wei, Zeming, et al.
Pubblicazione: (2026)

UCD: Unlearning in LLMs via Contrastive Decoding
di: Suriyakumar, Vinith M., et al.
Pubblicazione: (2025)

An Adversarial Perspective on Machine Unlearning for AI Safety
di: Łucki, Jakub, et al.
Pubblicazione: (2024)

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
di: Li, Na, et al.
Pubblicazione: (2024)

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
di: Xu, Xiaoyu, et al.
Pubblicazione: (2025)

Differential Privacy via Distributionally Robust Optimization
di: Selvi, Aras, et al.
Pubblicazione: (2023)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
di: Yuan, Hongbang, et al.
Pubblicazione: (2024)

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
di: Chen, Yen-Shan, et al.
Pubblicazione: (2026)

GSE: Group-wise Sparse and Explainable Adversarial Attacks
di: Sadiku, Shpresim, et al.
Pubblicazione: (2023)

Efficient Optimization Algorithms for Linear Adversarial Training
di: RIbeiro, Antônio H., et al.
Pubblicazione: (2024)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
di: Li, Nathaniel, et al.
Pubblicazione: (2024)

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
di: Jang, Yeonwoo, et al.
Pubblicazione: (2025)

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
di: Ribeiro, Antônio H., et al.
Pubblicazione: (2025)

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
di: Hou, Abe Bohan, et al.
Pubblicazione: (2024)

SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models
di: Dabiriaghdam, Amirhossein, et al.
Pubblicazione: (2025)

Second-Order Min-Max Optimization with Lazy Hessians
di: Chen, Lesi, et al.
Pubblicazione: (2024)

SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
di: Sun, Jialong, et al.
Pubblicazione: (2026)

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
di: Xu, Xiaoyu, et al.
Pubblicazione: (2025)

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
di: Islamov, Rustem, et al.
Pubblicazione: (2026)

Machine Unlearning Fails to Remove Data Poisoning Attacks
di: Pawelczyk, Martin, et al.
Pubblicazione: (2024)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
di: Zhu, Kaijie, et al.
Pubblicazione: (2023)

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
di: Brown, Hannah, et al.
Pubblicazione: (2024)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
di: Di, Jimmy Z., et al.
Pubblicazione: (2022)

Identifying and Understanding Cross-Class Features in Adversarial Training
di: Wei, Zeming, et al.
Pubblicazione: (2025)

SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models
di: Djuhera, Aladin, et al.
Pubblicazione: (2025)

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
di: Xue, Jiaqi, et al.
Pubblicazione: (2024)

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
di: An, Bang, et al.
Pubblicazione: (2024)

In the Name of Fairness: Assessing the Bias in Clinical Record De-identification
di: Xiao, Yuxin, et al.
Pubblicazione: (2023)

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
di: Li, Ran, et al.
Pubblicazione: (2025)

Learning Fair Robustness via Domain Mixup
di: Zhong, Meiyu, et al.
Pubblicazione: (2024)

LLM Unlearning Should Be Form-Independent
di: Ye, Xiaotian, et al.
Pubblicazione: (2025)

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
di: Muhamed, Aashiq, et al.
Pubblicazione: (2025)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
di: Kaneko, Masahiro, et al.
Pubblicazione: (2025)

Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks
di: Wang, Rui, et al.
Pubblicazione: (2025)