AI RESEARCH
Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems
arXiv CS.AI
•
ArXi:2601.14662v2 Announce Type: replace Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph structure remains unexplored under realistic query budgets. We study a budget-constrained black-box setting where an adversary adaptively queries the system to steal its latent entity-relation graph.