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

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.

@article{song2025_2505.18583,
  title={ The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems },
  author={ Hongru Song and Yu-an Liu and Ruqing Zhang and Jiafeng Guo and Jianming Lv and Maarten de Rijke and Xueqi Cheng },
  journal={arXiv preprint arXiv:2505.18583},
  year={ 2025 }
}