RAG system architectures show varied robustness to knowledge base poisoning

Researchers have investigated the vulnerability of Retrieval-Augmented Generation (RAG) systems to knowledge base poisoning, finding that system architecture significantly impacts adversarial robustness. Evaluations on the Natural Questions dataset revealed that architectures designed to handle conflicting information, such as Recursive Language Models (RLM), were substantially more resistant to poisoning attacks compared to vanilla RAG systems. The study indicated that adversarial framing, rather than retrieval optimization, was the primary driver of attack success for most architectures, highlighting the content-reasoning stage as a key vulnerability. AI

影响 Highlights architectural choices as critical for RAG system security against adversarial attacks, influencing future system design.

排序理由 Academic paper detailing a new evaluation of RAG system architectures against knowledge base poisoning. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• CorruptRAG-AK
• MADAM-RAG
• Natural Questions
• Recursive Language Models

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →