AI RESEARCH
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
arXiv CS.AI
•
ArXi:2604.02954v1 Announce Type: cross Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems nstrate inherent resistance to traditional RAG attacks, such as text poisoning and prompt injection.