用网页排名算法提升网络安全大模型的抗攻击能力
RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
- 在知识库中用PageRank评估文档可信度，识别恶意内容
- 在MS MARCO上降低恶意文档得分，提升可信内容权重
- 适合关注AI安全与威胁情报系统的研究人员
检索增强生成（RAG）已成为网络威胁情报（CTI）系统中应用大语言模型的主流架构。然而，该设计易受投毒攻击，现有防御方法在CTI场景下可能失效，因新兴攻击信息通常全新，且高级威胁者可模仿合法格式、术语和文风。为此，我们提出通过在语料库中应用源可信度算法（以PageRank为例）来加速现代RAG防御的鲁棒性。实验表明，该算法在标准MS MARCO数据集上能有效降低恶意文档的权威分，同时提升可信内容的权重；在真实CTI文档与数据流上也验证了其概念可行性。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber Threat Intelligence (CTI) systems. However, this design is susceptible to poisoning attacks, and previously proposed defenses can fail for CTI contexts as cyber threat information is often completely new for emerging attacks, and sophisticated threat actors can mimic legitimate formats, terminology, and stylistic conventions. To address this issue, we propose that the robustness of modern RAG defenses can be accelerated by applying source credibility algorithms on corpora, using PageRank as an example. In our experiments, we demonstrate quantitatively that our algorithm applies a lower authority score to malicious documents while promoting trusted content, using the standardized MS MARCO dataset. We also demonstrate proof-of-concept performance of our algorithm on CTI documents and feeds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。