Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowledge. Recently, there has been a trend of storing up-to-date or copyrighted data in RAG knowledge databases instead of using it for LLM training. This practice has raised concerns about Membership Inference Attacks (MIAs), which aim to detect if a specific target document is stored in the RAG system's knowledge database so as to protect the rights of data producers. While research has focused on enhancing the trustworthiness of RAG systems, existing MIAs for RAG systems remain largely insufficient. Previous work either relies solely on the RAG system's judgment or is easily influenced by other documents or the LLM's internal knowledge, which is unreliable and lacks explainability. To address these limitations, we propose a Mask-Based Membership Inference Attacks (MBA) framework. Our framework first employs a masking algorithm that effectively masks a certain number of words in the target document. The masked text is then used to prompt the RAG system, and the RAG system is required to predict the mask values. If the target document appears in the knowledge database, the masked text will retrieve the complete target document as context, allowing for accurate mask prediction. Finally, we adopt a simple yet effective threshold-based method to infer the membership of target document by analyzing the accuracy of mask prediction. Our mask-based approach is more document-specific, making the RAG system's generation less susceptible to distractions from other documents or the LLM's internal knowledge. Extensive experiments demonstrate the effectiveness of our approach compared to existing baseline models.
SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling
Sun Yat-Sen University(孙中山大学);Nanyang Technological University(南洋理工大学);University of Chinese Academy of Science(中国科学院大学);Zhongguancun Academy(中关村学院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
College of Cyber Security, Jinan University(济南大学网络安全学院);School of Computer Science, Shanghai Jiaotong University(上海交通大学计算机科学学院);Institute of Artificial Intelligence, Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University(北京航空航天大学人工智能研究院);Zhongguancun Laboratory, Beijing(中关村实验室)
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
University of California San Diego(加州大学圣地亚哥分校);Toyota Technological Institute at Chicago (TTIC)(芝加哥丰田技术研究所);University of Virginia(弗吉尼亚大学);National University of Singapore(新加坡国立大学)
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
Graduate School of Artificial Intelligence, POSTECH, Republic of Korea(人工智能研究生院,POSTECH,韩国);Department of Computer Science and Engineering, POSTECH, Republic of Korea(计算机科学与工程系,POSTECH,韩国)
DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
School of Cyber Science and Technology, Shandong University(山东大学计算机科学与技术学院);Department of Engineering Software, School of Civil Engineering, Shandong University(山东大学土木工程学院工程软件系);State Key Laboratory of Cryptography and Digital Economy Security, Shandong University(山东大学密码与数字经济安全国家重点实验室);Shandong Key Laboratory of Artificial Intelligence Security, Shandong University(山东省人工智能安全重点实验室)
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
Institute of Science Tokyo(东京科学大学);Nanyang Technological University(南洋理工大学);Tohoku University(东北大学);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Shandong University(山东大学)
Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
State Key Laboratory of Mathematical Engineering and Advanced Computing(数学工程与先进计算国家重点实验室);Information Engineering University(信息工程大学);Henan Key Laboratory of Information Security(河南省信息安全重点实验室);University of Chinese Academy of Sciences(中国科学院大学)
Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
Department of Electrical and Electronics Engineering(电子与电气工程系);Birla Institute of Technology and Science, Pilani, Pilani Campus(比拉理工学院和科学学院,比拉校区);Department of Computer Engineering, KIIT University(计算机工程系,KIIT大学);Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory(量子云计算与分布式系统(qCLOUDS)实验室);Department of Computing and Information Systems(计算与信息系统系);The University of Melbourne(墨尔本大学)