Metraipolis › archive › dc_cf27ddc7b73d
Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization — arXiv:2610.34829
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34829
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:58:12.128Z
- SHA-256 of the archived text
39714caed559ede3634b6d5998a495be334b8096afa29917722ed9ee15117d82- Stable URL of this page
https://metraipolis.com/documento/dc_cf27ddc7b73d
How to cite
Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization — arXiv:2610.34829 — arXiv (en), https://arxiv.org/abs/2610.34829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf27ddc7b73d (Metraipolis archive dc_cf27ddc7b73d, sha256 39714caed559ede3634b6d5998a495be334b8096afa29917722ed9ee15117d82)
BibTeX
@misc{dccf27ddc7b73d,
title = {Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization — arXiv:2610.34829},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34829},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf27ddc7b73d; sha256 39714caed559ede3634b6d5998a495be334b8096afa29917722ed9ee15117d82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on explicit factual refutations or imperative instruction overrides. Modern aligned LLMs often arbitrate such conflicts conservatively, rejecting overt contradictions in favor of parametric memory or clean retrieved context while triggering input guardrails. We propose MONOLOGUE, a single-document poisoning framework based on Logic Hijacking without explicit refutation. Rather than disputing the ground truth, our method concedes it as an authoritative historical baseline before introducing the update, weaving a grounded record-correction narrative (e.g., dated institutional reattributions) that presents the counterfactual target as the most recent update. To prevent suspicious live writes, payloads are refined entirely offline via local multi-dimensional gated optimization, coupling automated text quality audits with surrogate behavioral verification. Evaluations across three benchmarks, three retrieval backends, and four open-weight generator regimes show that our method achieves the strongest overall attack efficacy among the evaluated single-document poisoning attacks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34829 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.718Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).