# RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

arXiv: https://arxiv.org/abs/2411.18948 · HTML: https://mlsanity.com/paper/2411.18948/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Poisoning Retrieval Corpora by Injecting Adversarial Passages](https://mlsanity.com/paper/2310.19156/) (2023)
- [Certifiably Robust RAG against Retrieval Corruption](https://mlsanity.com/paper/2405.15556/) (2024)
- [Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations](https://mlsanity.com/paper/2404.13948/) (2024)
- [Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise](https://mlsanity.com/paper/2305.01579/) (2023)
- [Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking](https://mlsanity.com/paper/2311.06102/) (2023)
- [Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent](https://mlsanity.com/paper/2106.15023/) (2021)
- [Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks](https://mlsanity.com/paper/2309.13256/) (2023)
- [A LLM Assisted Exploitation of AI-Guardian](https://mlsanity.com/paper/2307.15008/) (2023)

## Built on by (most cited first, 30 of 35)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval](https://mlsanity.com/paper/2512.16962/) (2025)
- [A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle](https://mlsanity.com/paper/2604.16548/) (2026)
- [On the Fundamental Limits of LLMs at Scale](https://mlsanity.com/paper/2511.12869/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents](https://mlsanity.com/paper/2607.14651/) (2026)
- [RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning](https://mlsanity.com/paper/2510.10008/) (2025)
- [Towards Security-Auditable LLM Agents: A Unified Graph Representation](https://mlsanity.com/paper/2605.06812/) (2026)
- [Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention](https://mlsanity.com/paper/2602.04711/) (2026)
- [Security Considerations for Multi-agent Systems](https://mlsanity.com/paper/2603.09002/) (2026)
- [MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents](https://mlsanity.com/paper/2605.03482/) (2026)
- [FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems](https://mlsanity.com/paper/2509.24408/) (2025)
- [Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion](https://mlsanity.com/paper/2602.08668/) (2026)
- [Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG](https://mlsanity.com/paper/2602.21447/) (2026)
- [ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning](https://mlsanity.com/paper/2603.22934/) (2026)
- [Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2604.08304/) (2026)
- [One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness](https://mlsanity.com/paper/2604.27674/) (2026)
- [Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection](https://mlsanity.com/paper/2501.14728/) (2025)
- [ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering](https://mlsanity.com/paper/2603.13950/) (2026)
- [Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence](https://mlsanity.com/paper/2605.01782/) (2026)
- [Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control](https://mlsanity.com/paper/2605.26754/) (2026)
- [When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems](https://mlsanity.com/paper/2607.06807/) (2026)
- [When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse](https://mlsanity.com/paper/2608.06947/) (2026)
- [Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.24977/) (2026)
- [Towards Unsupervised Adversarial Document Detection in Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2603.17176/) (2026)
- [When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines](https://mlsanity.com/paper/2606.11265/) (2026)
- [Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution](https://mlsanity.com/paper/2606.25721/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.23838/) (2026)
- [RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.13010/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database, enabling them to produce responses that are more accurate and contextually appropriate. It is worth noting that the knowledge database, being sourced from publicly available channels such as Wikipedia, inevitably introduces a new attack surface. RAG poisoning involves injecting malicious texts into the knowledge database, ultimately leading to the generation of the attacker's target response (also called poisoned response). However, there are currently limited methods available for detecting such poisoning attacks. We aim to bridge the gap in this work. Particularly, we introduce RevPRAG, a flexible and automated detection pipeline that leverages the activations of LLMs for poisoned response detection. Our investigation uncovers distinct patterns in LLMs' activations when generating correct responses versus poisoned responses. Our results on multiple benchmark datasets and RAG architectures show our approach could achieve 98% true positive rate, while maintaining false positive rates close to 1%.