A single poisoned document that explicitly names and refutes the correct answer can steer RAG systems toward attacker-chosen wrong answers, with effects that vary by target model.
{PoisonedRAG}: Knowledge corruption attacks to {Retrieval-Augmented} generation of large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial
A single poisoned document that explicitly names and refutes the correct answer can steer RAG systems toward attacker-chosen wrong answers, with effects that vary by target model.