RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
On the map: Retrieval-augmented generation → Privacy and security of RAG
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 30 references that are in the map. First posted on arXiv 23 Oct 2025.
Builds on
17 of 30 references.
Closest ancestors · 7
Same direction, newest first
- 2025ClaimTrust: Propagation Trust Scoring for RAG Systems12 Mar
- 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation1 Jan
- 2024Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks21 Dec
- 2024ConfusedPilot: Confused Deputy Risks in RAG-based LLMs9 Aug
- 2024Certifiably Robust RAG against Retrieval Corruption24 May
- 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models12 Feb
- 2023Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation30 Dec
Other references · 10
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
- 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
- 2024CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligencecited by 61
- 2024LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTIcited by 17
- 2025Advancing Autonomous Incident Response: Leveraging LLMs and Cyber Threat Intelligencecited by 6
- 2025Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Modelscited by 5
- 2025False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systemscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs
- 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
- 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
- 2025RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation
- 2026RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
- 2025Secure Retrieval-Augmented Generation against Poisoning Attacks
- 2026Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text
- 2025The Hidden Threat in Plain Text: Attacking RAG Data Loaders