RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines

• URL: http://arxiv.org/abs/2510.20768v1
• Date: Thu, 23 Oct 2025 17:43:00 GMT
• Title: RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
• Abstract summary: Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber Threat Intelligence systems.<n>We propose that the robustness of modern RAG defenses can be accelerated by applying source credibility algorithms on corpora.
• Score: 0.9144793163215507
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models [20.029939692534292]
  This work investigates the vulnerability of neural ranking models to corpus poisoning attacks.<n>An adversary injects a small number of maliciously crafted documents into the corpus to distort ranking behavior.<n>We propose VerTox, the first framework to formulate corpus poisoning as a verifiable reward-guided reinforcement learning problem.
  arXiv  Detail & Related papers  (2026-09-01T14:43:11Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models [17.398369313076053]
  CRAFT is a supervised framework for black-box rank attacks powered by large language models (LLMs)<n>It outperforms state-of-the-art baselines in achieving higher promotion rates and rank boosts while preserving semantic fidelity.<n>This work underscores the risks of generative AI in rank manipulation, and provides a foundation for developing more robust retrieval systems.
  arXiv  Detail & Related papers  (2026-05-02T19:26:34Z)
• ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search [69.60882125603133]
  We present ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents.<n>Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.
  arXiv  Detail & Related papers  (2025-09-27T22:36:42Z)
• RAG Security and Privacy: Formalizing the Threat Model and Attack Surface [4.823988025629304]
  Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses.<n>Existing research has demonstrated that RAGs can leak sensitive information through training data memorization or adversarial prompts, and RAG systems inherit many of these vulnerabilities.<n>Despite these risks, there is currently no formal framework that defines the threat landscape for RAG systems.
  arXiv  Detail & Related papers  (2025-09-24T17:11:35Z)
• Algorithms for Adversarially Robust Deep Learning [58.656107500646364]
  We discuss recent progress toward designing algorithms that exhibit desirable robustness properties.<n>We present new algorithms that achieve state-of-the-art generalization in medical imaging, molecular identification, and image classification.<n>We propose new attacks and defenses, which represent the frontier of progress toward designing robust language-based agents.
  arXiv  Detail & Related papers  (2025-09-23T14:48:58Z)
• Graph Representation-based Model Poisoning on Federated Large Language Models [3.5233863453805143]
  Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy.<n>This article first reviews recent advancements in model poisoning techniques and existing defense mechanisms for FedLLMs, underscoring critical limitations.<n>The article further investigates graph representation-based model poisoning (GRMP), an emerging attack paradigm that exploits higher-order correlations among benign client gradients to craft malicious updates indistinguishable from legitimate ones.
  arXiv  Detail & Related papers  (2025-07-02T13:20:52Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Adversarial Training for Defense Against Label Poisoning Attacks [53.893792844055106]
  Label poisoning attacks pose significant risks to machine learning models.<n>We propose a novel adversarial training defense strategy based on support vector machines (SVMs) to counter these threats.<n>Our approach accommodates various model architectures and employs a projected gradient descent algorithm with kernel SVMs for adversarial training.
  arXiv  Detail & Related papers  (2025-02-24T13:03:19Z)
• OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities [0.0]
  We demonstrate a new approach to assessing AI's progress towards enabling and scaling real-world offensive cyber operations.<n>We detail OCCULT, a lightweight operational evaluation framework that allows cyber security experts to contribute to rigorous and repeatable measurement.<n>We find that there has been significant recent advancement in the risks of AI being used to scale realistic cyber threats.
  arXiv  Detail & Related papers  (2025-02-18T19:33:14Z)
• Reformulation is All You Need: Addressing Malicious Text Features in DNNs [53.45564571192014]
  We propose a unified and adaptive defense framework that is effective against both adversarial and backdoor attacks.<n>Our framework outperforms existing sample-oriented defense baselines across a diverse range of malicious textual features.
  arXiv  Detail & Related papers  (2025-02-02T03:39:43Z)
• CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models [49.657358248788945]
  Textual descriptions in cyber threat intelligence (CTI) reports are rich sources of knowledge about cyber threats.<n>Current CTI knowledge extraction methods lack flexibility and generalizability.<n>We propose CTINexus, a novel framework for data-efficient CTI knowledge extraction and high-quality cybersecurity knowledge graph (CSKG) construction.
  arXiv  Detail & Related papers  (2024-10-28T14:18:32Z)
• Cyber Knowledge Completion Using Large Language Models [1.4883782513177093]
  Integrating the Internet of Things (IoT) into Cyber-Physical Systems (CPSs) has expanded their cyber-attack surface. Assessing the risks of CPSs is increasingly difficult due to incomplete and outdated cybersecurity knowledge. Recent advancements in Large Language Models (LLMs) present a unique opportunity to enhance cyber-attack knowledge completion.
  arXiv  Detail & Related papers  (2024-09-24T15:20:39Z)
• Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks [4.576324217026666]
  Convolutional neural networks (CNNs) models play a vital role in achieving state-of-the-art performances. CNNs can be compromised because of their susceptibility to adversarial attacks. We present a novel and comprehensive method to improve the strength of attacks and assess the transferability of adversarial examples in CNNs.
  arXiv  Detail & Related papers  (2023-10-26T22:36:24Z)
• Looking Beyond IoCs: Automatically Extracting Attack Patterns from External CTI [3.871148938060281]
  LADDER is a framework that can extract text-based attack patterns from cyberthreat intelligence reports at scale. We present several use cases to demonstrate the application of LADDER in real-world scenarios.
  arXiv  Detail & Related papers  (2022-11-01T12:16:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.