RAG Security

RAG: Retrieval-Augmented Generation

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 74

All topics

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions
May 1, 2026Soumil Datta, Melissa Umble, Daniel S. Brown +1Prompt Injection Defense RAG Security
University of Utah
When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI
May 1, 2026Alfredo Madrid-García, Miguel RujasHealthcare LLM Auditing
Escuela Técnica Superior de Ingenieros de Telecomunicación Universidad Politécnica de Madrid Avenida Complutense, 30, Madrid, 28040, Spain
E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
May 1, 2026Zelin Guan, Shengda Zhuo, Zeyan Li +4Membership Inference Attacks Privacy Leakage in Language Models
College of Cyber Security, Jinan University, Guangzhou, China · School of Computer Science, Shanghai Jiaotong University, Shanghai, China · Institute of Artificial Intelligence, Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing 100191, China +1
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
May 1, 2026Weifei Jin, Xilong Wang, Wei Zou +2RAG Poisoning Attacks RAG Security
Duke University · The Pennsylvania State University
Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations
Apr 30, 2026Md Hasan Saju, Akramul AzimCybersecurity LLMs for Cybersecurity
† Department of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, Ontario, Canada
Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attacks
Apr 22, 2026Pranav Pallerla, Wilson Naik Bhukya, Bharath Vemula +1Autonomous Cyber Defense RAG Security
School of Computer and Information Sciences University of Hyderabad Hyderabad, Telangana, India · Purdue University West Lafayette, USA
Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Apr 20, 2026Wentao Zhang, Yan Zhuang, ZhuHang Zheng +3Retrieval-Augmented Generation RAG Security
University of Electronic Science and Technology of China, Chengdu, China · Shenzhen Institute for Advanced Study, UESTC, Shenzhen, China
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Apr 17, 2026Andreea-Elena Bodea, Stephen Meisenbacher, Florian MatthesRetrieval-Augmented Generation RAG Security
Technical University of Munich · School of Computation, Information and Technology · Garching, Germany
A Survey of Secure Retrieval-Augmented Generation
Apr 9, 2026Yuming Xu, Mingtao Zhang, Zhuohan Ge +7RAG Security RAG Robustness
The Hong Kong Polytechnic University · The Hong Kong University of Science and Technology (Guangzhou)
Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval
Nov 30, 2025Hao Wu, Prateek SaxenaAdversarial Attacks on LLMs LLM Security
National University of Singapore
Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
Oct 1, 2025Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1Language Model Steering RAG Poisoning Attacks
CyCraft AI Lab, Taiwan · National Taiwan University
Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG
Aug 4, 2025Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi +3RAG Security OOD Detection
New York University · Microsoft · University of Pennsylvania +1
Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models
Apr 14, 2025Yujing Wang, Jinwen Chen, Hainan Zhang +5Retrieval-Augmented Generation Privacy Leakage in Language Models
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence, Beihang University, China Beijing, China
BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
Jun 3, 2024Jiaqi Xue, Mengxin Zheng, Yebowen Hu +3LLM Backdoor Attacks RAG Poisoning Attacks
University of Central Florida · Emory University · Samsung Research America

May 1, 2026, cs.CRJ/K move · Enter open · S save

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions

Soumil Datta, Melissa Umble, Daniel S. Brown, Guanhong Tao

University of Utah

Prompt Injection Defense RAG Security Prompt Injection Attacks on LLMs Prompt Injection Detection

Open paper AskPDF arXiv

Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available attack surface, allowing adversaries to insert malicious instructions that trigger unintended model behaviors. Current defensive measures often utilize LLM-based detectors to filter such content, but these approaches remain vulnerable to optimization-based attacks. Additionally, training-based methods frequently fail to generalize to novel data distributions. To resolve these issues, we introduce SONAR, a prompt sanitization framework that identifies and removes injected content using metrics from natural language inference. Specifically, SONAR constructs a sentence-level relational graph across the user query and external data. By using entailment and contradiction scores as edge weights, the system identifies sentences that deviate from the core task. It then employs connectivity-driven pruning to eliminate flagged injection seeds and their related neighbors while maintaining benign context. Rigorous evaluations across several models and datasets show that SONAR reduces the attack success rate to nearly zero, significantly outperforming nine established baseline defenses.

Momentum

Related topics

Latest papers 74