Score: 1

Exposing Privacy Risks in Graph Retrieval-Augmented Generation

Published: August 24, 2025 | arXiv ID: 2508.17222v1

By: Jiale Liu, Jiahao Zhang, Suhang Wang

Potential Business Impact:

Finds secrets hidden in smart AI answers.

Business Areas:
Augmented Reality Hardware, Software

Retrieval-Augmented Generation (RAG) is a powerful technique for enhancing Large Language Models (LLMs) with external, up-to-date knowledge. Graph RAG has emerged as an advanced paradigm that leverages graph-based knowledge structures to provide more coherent and contextually rich answers. However, the move from plain document retrieval to structured graph traversal introduces new, under-explored privacy risks. This paper investigates the data extraction vulnerabilities of the Graph RAG systems. We design and execute tailored data extraction attacks to probe their susceptibility to leaking both raw text and structured data, such as entities and their relationships. Our findings reveal a critical trade-off: while Graph RAG systems may reduce raw text leakage, they are significantly more vulnerable to the extraction of structured entity and relationship information. We also explore potential defense mechanisms to mitigate these novel attack surfaces. This work provides a foundational analysis of the unique privacy challenges in Graph RAG and offers insights for building more secure systems.

Country of Origin
🇺🇸 United States


Page Count
14 pages

Category
Computer Science:
Cryptography and Security