跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.12241 · v1

SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations

首次提交 2026-11-09 19:30
版本更新 2026-11-09 19:30
雷达观测 2026-11-10 15:22
arXiv ↗PDF ↗

摘要

Retrieval-Augmented Generation (RAG) systems improve Large Language Model (LLM) responses by incorporating information from external knowledge bases. However, recent studies have shown that attackers can extract substantial portions of private knowledge bases from RAG systems through repeated querying. Yet, state-of-the-art extraction attacks either rely heavily on external LLMs to generate adversarial queries or require a large number of queries. In this paper, we propose SNAPRAG, a novel and cost-efficient attack for extracting RAG knowledge bases through adversarial perturbations. Our approach algorithmically generates adversarial queries without relying on external LLMs and allows for a strictly configurable query budget. In particular, SNAPRAG uses a discrete token-mutation algorithm to generate novel queries in a strict black-box setting. Our adaptive dissimilarity threshold calibration systematically forces queries into unexplored semantic regions of the target database, enabling extraction with fewer queries. Specifically, to extract half of the target knowledge base, our method requires up to 6.77×\times fewer queries than existing approaches. Furthermore, within a fixed query budget, our method recovers up to 96.9%, outperforming the closest approach by 7.7-19.9%. We further evaluate SNAPRAG against active defenses, where it remains the leading attack on four of five defended targets, achieving 50.7-96.3% extraction rate.

作者备注:20 pages, 6 figures, including appendices

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-09 19:30 · 最新观测版本

SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations

Retrieval-Augmented Generation (RAG) systems improve Large Language Model (LLM) responses by incorporating information from external knowledge bases. However, recent studies have shown that attackers can extract substantial portions of private knowledge bases from RAG systems through repeated querying. Yet, state-of-the-art extraction attacks either rely heavily on external LLMs to generate adversarial queries or require a large number of queries. In this paper, we propose SNAPRAG, a novel and cost-efficient attack for extracting RAG knowledge bases through adversarial perturbations. Our approach algorithmically generates adversarial queries without relying on external LLMs and allows for a strictly configurable query budget. In particular, SNAPRAG uses a discrete token-mutation algorithm to generate novel queries in a strict black-box setting. Our adaptive dissimilarity threshold calibration systematically forces queries into unexplored semantic regions of the target database, enabling extraction with fewer queries. Specifically, to extract half of the target knowledge base, our method requires up to 6.77×\times fewer queries than existing approaches. Furthermore, within a fixed query budget, our method recovers up to 96.9%, outperforming the closest approach by 7.7-19.9%. We further evaluate SNAPRAG against active defenses, where it remains the leading attack on four of five defended targets, achieving 50.7-96.3% extraction rate.

查看此版本解读 →查看此版本原文 ↗