Work

Defense Against Knowledge Poisoning Attack on GraphRAG

Year: 2026

Type: conference-paper

Abstract: GraphRAG augments large language models with structured knowledge graphs, enabling graph-based context selection and a more integrated view of the knowledge space.However, recent work shows that GraphRAG exposes a new attack surface: corpus-level knowledge poisoning can inject spurious entities and relationships during graph construction, corrupting query-specific subgraphs and steering the generator toward incorrect answers.We propose Hop-wise Guard for GraphRAG (HoG-GRAG), a defense layer between retriever and generator that decomposes multi-hop questions into ordered subqueries, monitors hop-wise execution for poisoning-induced inconsistencies, and locally repairs the retrieved subgraph by pruning compromised entities and relationships and adding only minimal missing evidence.Experiments on multi-hop datasets and multiple GraphRAG configurations show that HoG-GRAG recovers a large fraction of the lost performance.The code is available at https:// github.com/CyberScienceLab/HoG-GRAG.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-short.47

Authors: Havva Alizadeh Noughabi, Fattane Zarrinkalam, Ali Dehghantanha

Institution: University of Guelph

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Government of Canada, Natural Sciences and Engineering Research Council of Canada

Award: G4540027533