collaborators

8 papers

cs.LG2026

Machine Unlearning in Low-Dimensional Feature Subspace

Kun Fang, Qinghua Tao, Junxu Liu +4

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspectiv…

cs.CR2025

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

Yaxin Xiao, Qingqing Ye, Zi Liang +4

Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through…

cs.CR2025

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Zi Liang, Qingqing Ye, Xuan Liu +3

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during trainin…

cs.CR2025

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

Li Bai, Qingqing Ye, Xinwei Zhang +4

Machine learning models are often vulnerable to inference attacks that expose sensitive information from their training data. Shadow model technique is commonly employed in such at…

cs.CR2025

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks

Yuwen Pu, Zhou Feng, Chunyi Zhou +4

Recently, speech assistant and speech verification have been used in many fields, which brings much benefit and convenience for us. However, when we enjoy these speech applications…

cs.LG2025

Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy

Yaxin Xiao, Qingqing Ye, Li Hu +5

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to…