Metraipolis › archive › dc_b4525bfd883b

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework — arXiv:2608.04366

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04366
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:42.234Z
SHA-256 of the archived text
abd6ded32a43455a3cd42a5d55fca8a6b0a96babaae419d368ed7652e6b3636a
Stable URL of this page
https://metraipolis.com/documento/dc_b4525bfd883b

How to cite

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework — arXiv:2608.04366 — arXiv (en), https://arxiv.org/abs/2608.04366 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4525bfd883b (Metraipolis archive dc_b4525bfd883b, sha256 abd6ded32a43455a3cd42a5d55fca8a6b0a96babaae419d368ed7652e6b3636a)
BibTeX
@misc{dcb4525bfd883b,
  title = {Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework — arXiv:2608.04366},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04366},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4525bfd883b; sha256 abd6ded32a43455a3cd42a5d55fca8a6b0a96babaae419d368ed7652e6b3636a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04366. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, we propose SecureCollaRAG, a Byzantine-tolerant collaborative RAG framework leveraging Multi-source Knowledge Validation Mechanism. Our approach enables agent system to securely verify document provenance through dynamic GNN-based credibility scoring, effectively preventing stealthy knowledge corruption attacks while preserving essential domain knowledge integrity. Through extensive evaluations and formal analysis, we demonstrate that SecureCollaRAG maintains robustness against attackers under non-IID data distributions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04366 — 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 2026-10-31T11:02:13.499Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).