paper-with-me

Papers

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

2025-05-24 · Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Jianming Lv, Maarten de Rijke, Xueqi Cheng

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.

📄 PDF Abstract BibTeX arXiv:2505.18583

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationQuestion AnsweringRAGRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
WordPiece 설명 없음
Weight Decay 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Imperceptible Jailbreaking against Large Language Models

2025-10-06 · Kuofeng Gao, Yiming Li, Chao Du, Xin Wang 외 arxiv

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic su…

Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks

2020-12-01 · Christian Cosgrove, Adam Kortylewski, Chenglin Yang, Alan Yuille

Patch-based adversarial attacks introduce a perceptible but localized change to the input that induces misclassification. While progress has been made in defending against imperceptible attacks, it remains unclear how pa…

Traffic Sign Recognition

Perceptual Adversarial Robustness: Generalizable Defenses Against Unforeseen Threat Models

2021-01-01 · ICLR 2021 1 · Cassidy Laidlaw, Sahil Singla, Soheil Feizi

A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the definition of adversarial attacks that are imperceptible to human eyes. Most current attac…

Adversarial DefenseAdversarial RobustnessPerceptual Distance

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks

2024-12-15 · Jin Li, Zitong Yu, Ziqiang He, Z. Jane Wang 외

Imperceptible adversarial attacks have recently attracted increasing research interests. Existing methods typically incorporate external modules or loss terms other than a simple $l_p$-norm into the attack process to ach…

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models

2020-06-22 · Cassidy Laidlaw, Sahil Singla, Soheil Feizi

A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the very definition of adversarial attacks that are imperceptible to human eyes. Most current …

Adversarial DefenseAdversarial RobustnessPerceptual Distance