Metraipolis › archive › dc_bed7148e8255

RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation — arXiv:2609.25469

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25469
License (as archived)
CC0-1.0
Archived
2026-10-08T13:45:01.492Z
SHA-256 of the archived text
58d5ff4e0148929a550116238cc19746da8039e583cb397140e93c96c8d47641
Stable URL of this page
https://metraipolis.com/documento/dc_bed7148e8255

How to cite

RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation — arXiv:2609.25469 — arXiv (en), https://arxiv.org/abs/2609.25469 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bed7148e8255 (Metraipolis archive dc_bed7148e8255, sha256 58d5ff4e0148929a550116238cc19746da8039e583cb397140e93c96c8d47641)
BibTeX
@misc{dcbed7148e8255,
  title = {RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation — arXiv:2609.25469},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25469},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bed7148e8255; sha256 58d5ff4e0148929a550116238cc19746da8039e583cb397140e93c96c8d47641},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25469. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable external knowledge, yet their structural reliance on a dynamic retrieval pipeline introduces a largely unexplored class of adversarial vulnerability. Existing knowledge-base poisoning attacks are fundamentally static. Adversarial documents are pre-computed and injected without any awareness of what the victim system will actually retrieve for a given query, leaving the attack blind to the competitive documentary landscape that surrounds its payload in the generator's context window. Unlike traditional static poisoning attacks that are blind to the retrieved context, we introduce RAG-NAROK (Retrieval-Anchored Generation Negation And Response Quality Collapse), a RAG attack framework that adapts to the query text. RAG-NAROK exploits the transparency inherent in RAG pipeline to first extract the legitimate source identities, then generate Anchor-Specific Refutation documents that explicitly name and devalue retrieved sources while leveraging recency and authority biases to steer the text generation toward a target answer. Our results demonstrate that RAG-NAROK significantly outperforms static baselines across diverse domains, revealing a fundamental tension between RAG transparency and AI security.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25469 — 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 2026-10-08T13:18:38.085Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).