activity
20232025
collaborators

7 papers

cs.CL2025

A Survey on Unlearning in Large Language Models

Ruichen Qiu, Jiajun Tan, Jiayue Pu +3

Large Language Models (LLMs) demonstrate remarkable capabilities, but their training on massive corpora poses significant risks from memorized sensitive information. To mitigate th…

cs.LG2024

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection

Yihan Wang, Yiwei Lu, Xiao-Shan Gao +2

Availability attacks, or unlearnable examples, are defensive techniques that allow data owners to modify their datasets in ways that prevent unauthorized machine learning models fr…

cs.LG2024

MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation

Yihan Wang, Yiwei Lu, Guojun Zhang +4

Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for…

cs.LG2024

Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously

Yihan Wang, Yifan Zhu, Xiao-Shan Gao

Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release. Idea…

cs.LG2024

Game-Theoretic Unlearnable Example Generator

Shuang Liu, Yihan Wang, Xiao-Shan Gao

Unlearnable example attacks are data poisoning attacks aiming to degrade the clean test accuracy of deep learning by adding imperceptible perturbations to the training samples, whi…

cs.LG2024

Data-Dependent Stability Analysis of Adversarial Training

Yihan Wang, Shuang Liu, Xiao-Shan Gao

Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-bas…