# MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks

arXiv: https://arxiv.org/abs/2502.17832 · HTML: https://mlsanity.com/paper/2502.17832/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Demystifying Prompts in Language Models via Perplexity Estimation](https://mlsanity.com/paper/2212.04037/) (2022)
- [MultiModalQA: Complex Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2104.06039/) (2021)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [On the Adversarial Robustness of Multi-Modal Foundation Models](https://mlsanity.com/paper/2308.10741/) (2023)
- [Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents](https://mlsanity.com/paper/2406.05870/) (2024)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (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)
- [CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.03323/) (2023)
- ["Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models](https://mlsanity.com/paper/2406.19417/) (2024)
- [RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models](https://mlsanity.com/paper/2407.05131/) (2024)

## Built on by (most cited first, 26 of 26)

- [On the Fundamental Limits of LLMs at Scale](https://mlsanity.com/paper/2511.12869/) (2025)
- [ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search](https://mlsanity.com/paper/2509.23519/) (2025)
- [One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image](https://mlsanity.com/paper/2504.02132/) (2025)
- [Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning](https://mlsanity.com/paper/2604.16966/) (2026)
- [HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented Generation](https://mlsanity.com/paper/2511.15435/) (2025)
- [Security Considerations for Multi-agent Systems](https://mlsanity.com/paper/2603.09002/) (2026)
- [Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation](https://mlsanity.com/paper/2507.23229/) (2025)
- [NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding](https://mlsanity.com/paper/2601.01095/) (2026)
- [MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.28009/) (2026)
- [How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG System](https://mlsanity.com/paper/2508.17215/) (2025)
- [Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation](https://mlsanity.com/paper/2511.19257/) (2025)
- [Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models](https://mlsanity.com/paper/2601.19060/) (2026)
- [Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents](https://mlsanity.com/paper/2607.15657/) (2026)
- [AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs](https://mlsanity.com/paper/2505.11557/) (2025)
- [Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment](https://mlsanity.com/paper/2506.10030/) (2025)
- [Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG](https://mlsanity.com/paper/2602.06495/) (2026)
- [Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2603.00172/) (2026)
- [Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures](https://mlsanity.com/paper/2605.25435/) (2026)
- [Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.24977/) (2026)
- [CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation](https://mlsanity.com/paper/2609.02774/) (2026)
- [VLMs Can Aggregate Scattered Training Patches](https://mlsanity.com/paper/2506.03614/) (2025)
- [Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.10253/) (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)
- [DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption](https://mlsanity.com/paper/2608.16536/) (2026)
- [Vis-Poison: Poisoning Visual Knowledge in Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.20756/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) has become a common practice in multimodal large language models (MLLM) to enhance factual grounding and reduce hallucination. Yet, its reliance on retrieval exposes MLLMs to knowledge poisoning attacks, in which adversaries deliberately inject malicious multimodal content into external knowledge bases to steer models toward generating incorrect or even harmful responses. We present MM-PoisonRAG, a framework to systematically study the vulnerability of multimodal RAG under knowledge poisoning. Specifically, we design two novel attack strategies: Localized Poisoning Attack (LPA), which implants targeted, query-specific multimodal misinformation to manipulate outputs toward attacker-controlled responses, and Globalized Poisoning Attack (GPA), which uses a single, untargeted adversarial injection to broadly corrupt reasoning and collapse generation quality across all queries. Extensive experiments on diverse tasks, multimodal RAG components, and attacker access levels reveal severe vulnerabilities: LPA achieves up to 56% attack success rate even under restricted access, and transfers effectively across four different retrievers without re-optimizing the adversaries. GPA completely disrupts model generation to 0% accuracy with just one poisoned content. Moreover, both LPA and GPA bypass existing defenses, underscoring the fragility of multimodal RAG and establishing MM-PoisonRAG as a foundation for future research on securing RAG frameworks against multimodal knowledge poisoning.