Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization

The paper introduces MONOLOGUE, a single‑document poisoning framework that uses logic hijacking to subtly alter Retrieval‑Augmented Generation (RAG) outputs without overt contradictions. Instead of directly refuting facts, MONOLOGUE frames updates as authoritative historical corrections, embedding counterfactuals into a grounded narrative. The method refines payloads offline through local multi‑dimensional gated optimization, combining text quality audits with surrogate behavioral verification, and demonstrates superior attack efficacy across multiple benchmarks, retrieval backends, and open‑weight generators.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• rag
• benchmarks
• safety