AIBearisharXiv – CS AI · Apr 66/10
🧠
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
Researchers have discovered LogicPoison, a new attack method that exploits vulnerabilities in Graph-based Retrieval-Augmented Generation (GraphRAG) systems by corrupting logical connections in knowledge graphs without altering text semantics. The attack successfully bypasses GraphRAG's existing defenses by targeting the topological integrity of underlying graphs, significantly degrading AI system performance.