Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation

TL;DR

This paper introduces the first comprehensive benchmark for evaluating knowledge-extraction attacks and defenses on Retrieval-Augmented Generation systems, standardizing evaluation protocols across diverse models and datasets.

Contribution

It provides a unified, reproducible framework for assessing attack and defense strategies on RAG systems, addressing the fragmented research landscape.

Findings

Benchmark covers multiple attack and defense strategies.

Standardized evaluation protocols across datasets.

Insights into the effectiveness of various defenses.

Abstract

Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory management. However, recent studies show that knowledge-extraction attacks can recover sensitive knowledge-base content through maliciously crafted queries, raising serious concerns about intellectual property theft and privacy leakage. While prior work has explored individual attack and defense techniques, the research landscape remains fragmented, spanning heterogeneous retrieval embeddings, diverse generation models, and evaluations based on non-standardized metrics and inconsistent datasets. To address this gap, we introduce the first systematic benchmark for knowledge-extraction attacks on RAG systems. Our benchmark covers a broad spectrum of attack and defense strategies, representative retrieval embedding models, and both open- and closed-source generators, all evaluated under a unified experimental framework with standardized protocols across multiple datasets. By consolidating the experimental landscape and enabling reproducible, comparable evaluation, this benchmark provides actionable insights and a practical foundation for developing privacy-preserving RAG systems in the face of emerging knowledge extraction threats. Our code is available here.