New TopoGuard defense tackles split-knowledge attacks in RAG systems

A new defense mechanism called TopoGuard has been developed to combat split-knowledge attacks targeting retrieval-augmented generation (RAG) systems. These attacks involve injecting seemingly benign documents that, when combined, create false associations and mislead language models. TopoGuard utilizes graph theory to build a semantic similarity graph of retrieved documents, enabling the detection of malicious topologies. Experiments show TopoGuard variants are highly effective, catching significantly more attacks than existing filters like LlamaGuard-2-8B with low latency and robustness. AI

IMPACT Enhances the security and reliability of RAG systems against sophisticated adversarial attacks.

RANK_REASON The cluster contains a research paper detailing a new defense mechanism for RAG systems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• HotpotQA
• LlamaGuard
• LlamaGuard-2-8B
• retrieval-augmented generation
• split-knowledge attacks
• TopoGuard

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →