Image de couverture de livre

An Adversarial Perspective on Machine Unlearning for AI Safety

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Łucki, Jakub, Wei, Boyi, Huang, Yangsibo, Henderson, Peter, Tramèr, Florian, Rando, Javier
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Universal Jailbreak Backdoors from Poisoned Human Feedback
par: Rando, Javier, et autres
Publié: (2023)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
par: Rando, Javier, et autres
Publié: (2024)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
par: Carlini, Nicholas, et autres
Publié: (2025)

Query-Based Adversarial Prompt Generation
par: Hayase, Jonathan, et autres
Publié: (2024)

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
par: Rando, Javier, et autres
Publié: (2025)

What is in Your Safe Data? Identifying Benign Data that Breaks Safety
par: He, Luxi, et autres
Publié: (2024)

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

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

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
par: Shumailov, Ilia, et autres
Publié: (2024)

Machine Unlearning of Pre-trained Large Language Models
par: Yao, Jin, et autres
Publié: (2024)

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

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
par: Huang, Tao, et autres
Publié: (2024)

Certifying LLM Safety against Adversarial Prompting
par: Kumar, Aounon, et autres
Publié: (2023)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
par: Nikolić, Kristina, et autres
Publié: (2025)

Textual Unlearning Gives a False Sense of Unlearning
par: Du, Jiacheng, et autres
Publié: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
par: Wu, Xiaoyu, et autres
Publié: (2025)

Gradient-based Jailbreak Images for Multimodal Fusion Models
par: Rando, Javier, et autres
Publié: (2024)

Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
par: To, Bang Trinh Tran, et autres
Publié: (2025)

Are aligned neural networks adversarially aligned?
par: Carlini, Nicholas, et autres
Publié: (2023)

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

FIT to Forget: Robust Continual Unlearning for Large Language Models
par: Xu, Xiaoyu, et autres
Publié: (2026)

Laundering AI Authority with Adversarial Examples
par: Zhang, Jie, et autres
Publié: (2026)

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
par: Liu, Zesen, et autres
Publié: (2024)

Intent Laundering: AI Safety Datasets Are Not What They Seem
par: Golchin, Shahriar, et autres
Publié: (2026)

Trustworthy AI: Safety, Bias, and Privacy -- A Survey
par: Fang, Xingli, et autres
Publié: (2025)

Large-scale online deanonymization with LLMs
par: Lermen, Simon, et autres
Publié: (2026)

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
par: Hönig, Robert, et autres
Publié: (2024)

LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
par: Spracklen, Joseph, et autres
Publié: (2026)

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
par: Xu, Xiaoyu, et autres
Publié: (2026)

Fight Back Against Jailbreaking via Prompt Adversarial Tuning
par: Mo, Yichuan, et autres
Publié: (2024)

Blind Baselines Beat Membership Inference Attacks for Foundation Models
par: Das, Debeshee, et autres
Publié: (2024)

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies
par: Parmar, Manojkumar, et autres
Publié: (2025)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
par: Chen, Taiye, et autres
Publié: (2025)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
par: Li, Jianwei, et autres
Publié: (2025)

Adversarial Search Engine Optimization for Large Language Models
par: Nestaas, Fredrik, et autres
Publié: (2024)

On the Role of Attention Heads in Large Language Model Safety
par: Zhou, Zhenhong, et autres
Publié: (2024)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
par: Gu, Tianle, et autres
Publié: (2025)

FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning
par: Shaik, Thanveer, et autres
Publié: (2023)

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
par: Liu, Zheyuan, et autres
Publié: (2023)

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
par: Wang, Zeng, et autres
Publié: (2025)