Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
On the map: Retrieval-augmented generation → Privacy and security of RAG
also in 1 more
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 32 references that are in the map. First posted on arXiv 5 Aug 2026.
Builds on
19 of 32 references.
Closest ancestors · 3
Same direction, newest first
- 2025Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation4 Aug
- 2024Certifiably Robust RAG against Retrieval Corruption24 May
- 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models12 Feb
Other references · 16
- 2023GPT-4 Technical Reportcited by 18,132
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
- 2023A Survey of Large Language Modelscited by 2,537
- 2024Qwen2 Technical Reportcited by 2,076
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
- 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 378
- 2018Differentially Private Generative Adversarial Networkcited by 235
- 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 153
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
4 more
- 2023GEO: Generative Engine Optimizationcited by 53
- 2025Clinical ModernBERT: An efficient and long context encoder for biomedical textcited by 26
- 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
- 2024DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Promptscited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
- 2026Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
- 2025One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
- 2025UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
- 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
- 2026CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance
- 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases
- 2026Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems