Skip to main navigation Skip to search Skip to main content

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

  • Zhaoqi Wang
  • , Daqing He
  • , Zijian Zhang*
  • , Ye Liu
  • , Jiamou Liu
  • , Zhirui Zeng
  • , Zhan Qin
  • , Zhen Li
  • , Xin Li
  • , Hongwei Yao
  • , Jincheng An
  • , Yong Liu*
  • , Yi Li
  • , Qi Sun
  • , Xiulei Liu
  • , Liehuang Zhu
  • *Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

9 Downloads (CityUHK Scholars)

Abstract

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. © 2026 Owner/Author.
Original languageEnglish
Title of host publicationWWW '26 - Proceedings of the ACM Web Conference 2026
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery
Pages2661-2672
Number of pages12
ISBN (Print)9798400723070
DOIs
Publication statusPublished - Apr 2026
Event35th ACM Web Conference (WWW 2026) - Dubai, United Arab Emirates
Duration: 29 Jun 2026 → 3 Jul 2026

Publication series

NameWWW - Proceedings of the ACM Web Conference

Conference

Conference35th ACM Web Conference (WWW 2026)
Abbreviated titleWWW ’26
PlaceUnited Arab Emirates
CityDubai
Period29/06/26 → 3/07/26

Funding

This paper is supported by National Key Research and Development Program of China under the grant No.2023YFF0905300, National Natural Science Foundation of China under Grant U2468205.

Research Keywords

  • graph neural network
  • knowledge corruption attacks
  • large language model
  • retrieval-augmented generation
  • securecollarag

Publisher's Copyright Statement

  • This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Fingerprint

Dive into the research topics of 'Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework'. Together they form a unique fingerprint.

Cite this