RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915677647929344 |
|---|---|
| author | Jia, Austin Ramesh, Avaneesh Shamsi, Zain Zhang, Daniel Liu, Alex |
| author_facet | Jia, Austin Ramesh, Avaneesh Shamsi, Zain Zhang, Daniel Liu, Alex |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines Jia, Austin Ramesh, Avaneesh Shamsi, Zain Zhang, Daniel Liu, Alex Cryptography and Security Artificial Intelligence Information Retrieval 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. |
| title | RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines |
| topic | Cryptography and Security Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2510.20768 |