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
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.
Create a lesson
Related papers
Analog Pin Directionality as an Exfiltration Attack Surface in Mixed-Signal ICs
Ramana Ranganatham, Chirag Adiga, Michael Zuzak et al.
Characterizing Network Centralization and Observability in the Remote MCP Ecosystem
Muhammad Abdullah Sohail
When Agents Look Like Beacons: NIDS Evasion by Model Context Protocol Traffic
Muhammad Abdullah Sohail
Hamming Ideals and Grobner Bases for ISD-like Syndrome Decoding
Roberto La Scala, Marco Marchesin, Sharwan K. Tiwari
ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
Guosen Wu, Huizhen Huang, Guoxiong Long et al.
CASHEWS: Source Preprocessor for LLM-based Malicious Package Detection
Jean-Charles Noirot Ferrand, David Adei, Anders Møller et al.