Metraipolis › archive › dc_2990586ccfaa

Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems — arXiv:2610.21464

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21464
License (as archived)
CC0-1.0
Archived
2026-10-16T10:19:21.826Z
SHA-256 of the archived text
49dc36199f080350084d3e25ed4c86c4b9b7c6aaaca3ec836e74eb06f53d7ffb
Stable URL of this page
https://metraipolis.com/documento/dc_2990586ccfaa

How to cite

Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems — arXiv:2610.21464 — arXiv (en), https://arxiv.org/abs/2610.21464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2990586ccfaa (Metraipolis archive dc_2990586ccfaa, sha256 49dc36199f080350084d3e25ed4c86c4b9b7c6aaaca3ec836e74eb06f53d7ffb)
BibTeX
@misc{dc2990586ccfaa,
  title = {Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems — arXiv:2610.21464},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21464},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2990586ccfaa; sha256 49dc36199f080350084d3e25ed4c86c4b9b7c6aaaca3ec836e74eb06f53d7ffb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented generation (RAG) mitigates hallucinations and knowledge staleness in large language models using external knowledge. However, ingestion from public and third-party sources exposes RAG systems to poisoning attacks. Existing attacks are designed and evaluated under exact retrieval, where poisoned documents participate in global ranking. Deployment-scale systems instead rely on approximate nearest-neighbor (ANN) indexes such as hierarchical navigable small world (HNSW), where limited search budgets, graph-search reachability, and local benign-document competition invalidate this assumption and degrade existing attacks. We present a topology-aware topic-level poisoning attack against large-scale HNSW-RAG that generalizes to unseen topic queries. We organize poisoned documents into a Hub-Satellite structure: Satellites provide competitive entry points across semantic regions, while Hubs strengthen local cohesion and facilitate cascading retrieval. For generation, we propose an entity-claim promotion attack combining evidence anchoring and entity-claim coupling to promote the target entity via a target claim across different query regions. On 2M-document Wikipedia, our attack maintains over 72% retrieval success and reaches 31.29% attack success, substantially outperforming baselines; domain-specific experiments further support its effectiveness. Structural analyses show that the Hub-Satellite topology forms in HNSW, indicating that graph structure contributes to improved poisoned-document retrieval. Existing poisoning defenses cannot mitigate the attack, exposing graph-structural risks in HNSW-RAG systems.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.21464 — 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 2026-10-16T08:47:32.611Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).