3 papers
cs.CR2024
Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
Yuying Li, Gaoyang Liu, Chen Wang +1
Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retriev…
cs.CR2021
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
Jian Chen, Xuxin Zhang, Rui Zhang +2
Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can…
cs.LG2020
Federated Unlearning
Gaoyang Liu, Xiaoqiang Ma, Yang Yang +2
Federated learning (FL) has recently emerged as a promising distributed machine learning (ML) paradigm. Practical needs of the "right to be forgotten" and countering data poisoning…