Characterizing the blast radius of triple level poisoning attacks in knowledge graph retrieval augmented generation systems

KG-RAG (Knowledge Graph RAG) systems link entities by typed relational edges and support multi-hop reasoning chains in which one corrupted fact can spread across many inference paths at once. In this paper, we formally define and quantitatively assess the blast radius (corrupted queries per injected triple) of three triple-level poisoning strategies on Knowledge Graph RAG: edge poisoning, hub poisoning, and chain poisoning. Experiments on a biomedical knowledge graph built with Microsoft GraphRAG v0.3.6 and Gemma 2 9B show hub poisoning reaches a blast radius of $$14.0\times $$ , against $$7.0\times $$ for edge poisoning and $$4.0\times $$ per triple for chain poisoning, from a $$0\%$$ pre-poisoning baseline. Two-hop queries show the steadiest effect, and cascade corruption exceeds direct impact in every condition. We implement a graph-aware defense based on a degree-weighted trust score that uses entity centrality as a proxy for injection risk. At the reported operating point the filter queues the hub injection and $$4.1\%$$ of baseline triples, and does not queue the edge or chain injections.

Authors

Institutions

Publication Details

Journal
Discover Artificial Intelligence
Published
2026-11-13
DOI
https://doi.org/10.1007/s44163-026-02733-8
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Characterizing the blast radius of triple level poisoning attacks in knowledge graph retrieval augmented generation systems

Jasmine K S, Shree Raksha H R
1 links
Discover Artificial Intelligence
Adversarial Robustness in Machine Learning
article

Characterizing the blast radius of triple level poisoning attacks in knowledge graph retrieval augmented generation systems

Jasmine K S, Shree Raksha H R
article en

Abstract

KG-RAG (Knowledge Graph RAG) systems link entities by typed relational edges and support multi-hop reasoning chains in which one corrupted fact can spread across many inference paths at once. In this paper, we formally define and quantitatively assess the blast radius (corrupted queries per injected triple) of three triple-level poisoning strategies on Knowledge Graph RAG: edge poisoning, hub poisoning, and chain poisoning. Experiments on a biomedical knowledge graph built with Microsoft GraphRAG v0.3.6 and Gemma 2 9B show hub poisoning reaches a blast radius of $$14.0\times $$ , against $$7.0\times $$ for edge poisoning and $$4.0\times $$ per triple for chain poisoning, from a $$0\%$$ pre-poisoning baseline. Two-hop queries show the steadiest effect, and cascade corruption exceeds direct impact in every condition. We implement a graph-aware defense based on a degree-weighted trust score that uses entity centrality as a proxy for injection risk. At the reported operating point the filter queues the hub injection and $$4.1\%$$ of baseline triples, and does not queue the edge or chain injections.

Discover Artificial IntelligenceVol. 6(1)
R.V. College of Engineering (IN)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon