# The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems

arXiv: https://arxiv.org/abs/2505.18583 · HTML: https://mlsanity.com/paper/2505.18583/

## Key facts

- Cited by 10 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 32 of its 39 references that are in the map.
- First posted on arXiv 24 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [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)
- [A Multi-Task Embedder For Retrieval Augmented LLMs](https://mlsanity.com/paper/2310.07554/) (2023)
- [Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation](https://mlsanity.com/paper/2405.20485/) (2024)
- [Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval](https://mlsanity.com/paper/2203.05765/) (2022)
- [PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models](https://mlsanity.com/paper/2204.01321/) (2022)
- [Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models](https://mlsanity.com/paper/2209.06506/) (2022)
- [Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method](https://mlsanity.com/paper/2308.09861/) (2023)
- [SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback](https://mlsanity.com/paper/2410.18141/) (2024)
- [Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models](https://mlsanity.com/paper/2304.14867/) (2023)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [Multi-granular Adversarial Attacks against Black-box Neural Ranking Models](https://mlsanity.com/paper/2404.01574/) (2024)
- [Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off](https://mlsanity.com/paper/2312.10329/) (2023)

## Built on by (most cited first, 10 of 10)

- [Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems](https://mlsanity.com/paper/2601.07072/) (2026)
- [RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations](https://mlsanity.com/paper/2510.11195/) (2025)
- [UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.18652/) (2025)
- [Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2604.08304/) (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)
- [BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation](https://mlsanity.com/paper/2605.20123/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks](https://mlsanity.com/paper/2608.04286/) (2026)
- [Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems](https://mlsanity.com/paper/2609.21573/) (2026)

## Abstract (arXiv)

We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible retrieve-to-generate attack against RAG. This task aims to find imperceptible perturbations that retrieve a target document, originally excluded from the initial top-k candidate set, in order to influence the final answer generation. To address this task, we propose ReGENT, a reinforcement learning-based framework that tracks interactions between the attacker and the target RAG and continuously refines attack strategies based on relevance-generation-naturalness rewards. Experiments on newly constructed factual and non-factual question-answering benchmarks demonstrate that ReGENT significantly outperforms existing attack methods in misleading RAG systems with small imperceptible text perturbations.