CyberRAG: An agentic RAG cyber attack classification and reporting tool

• URL: http://arxiv.org/abs/2507.02424v1
• Date: Thu, 03 Jul 2025 08:32:19 GMT
• Title: CyberRAG: An agentic RAG cyber attack classification and reporting tool
• Authors: Francesco Blefari, Cristian Cosentino, Francesco Aurelio Pironti, Angelo Furfaro, Fabrizio Marozzo,
• Abstract summary: CyberRAG is a modular, agent-based framework that delivers real-time classification, explanation, and structured reporting for cyber-attacks.<n>Unlike traditional RAG systems, CyberRAG embraces an agentic design that enables dynamic control flow and adaptive reasoning.<n>CyberRAG has been evaluated achieving over 94% accuracy per class and pushing final classification accuracy to 94.92%.
• Score: 1.0345929832241807
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming security analysts with logs that demand deep, rapidly evolving domain expertise. Conventional machine-learning detectors trim the alert volume but still yield high false-positive rates, while standard single-pass Retrieval-Augmented Generation (RAG) pipelines often retrieve irrelevant context and fail to justify their predictions. To overcome these shortcomings, we present CyberRAG, a modular, agent-based RAG framework that delivers real-time classification, explanation, and structured reporting for cyber-attacks. A central LLM agent orchestrates (i) a pool of fine-tuned specialized classifiers, each tailored to a distinct attack family; (ii) tool adapters for enrichment and alerting; and (iii) an iterative retrieval-and-reason loop that continuously queries a domain-specific knowledge base until the evidence is both relevant and self-consistent. Unlike traditional RAG systems, CyberRAG embraces an agentic design that enables dynamic control flow and adaptive reasoning. This agent-centric architecture refines its threat labels and natural-language justifications autonomously, reducing false positives and enhancing interpretability. The framework is fully extensible: new attack types can be supported by simply adding a classifier without retraining the core agent. CyberRAG has been evaluated achieving over 94% accuracy per class and pushing final classification accuracy to 94.92% through semantic orchestration. Generated explanations score up to 0.94 in BERTScore and 4.9/5 in GPT-4-based expert evaluation. These results show that agentic, specialist-oriented RAG can pair high detection accuracy with trustworthy, SOC-ready prose, offering a practical and scalable path toward semi-autonomous cyber-defence workflows.

Related papers

• Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems [0.0]
  Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols.<n>One such risk is a cascading risk: a breach in one agent can cascade through the system, compromising others by exploiting inter-agent trust.<n>In an ACI attack, a malicious input or tool exploit injected at one agent leads to cascading compromises and amplified downstream effects across agents that trust its outputs.
  arXiv  Detail & Related papers  (2025-07-23T13:51:28Z)
• Hybrid LLM-Enhanced Intrusion Detection for Zero-Day Threats in IoT Networks [6.087274577167399]
  This paper presents a novel approach to intrusion detection by integrating traditional signature-based methods with the contextual understanding capabilities of the GPT-2 Large Language Model (LLM)<n>We propose a hybrid IDS framework that merges the robustness of signature-based techniques with the adaptability of GPT-2-driven semantic analysis.<n> Experimental evaluations on a representative intrusion dataset demonstrate that our model enhances detection accuracy by 6.3%, reduces false positives by 9.0%, and maintains near real-time responsiveness.
  arXiv  Detail & Related papers  (2025-07-10T04:10:03Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation [31.231916859341865]
  TrustRAG is a framework that systematically filters malicious and irrelevant content before it is retrieved for generation.<n>TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.
  arXiv  Detail & Related papers  (2025-01-01T15:57:34Z)
• LLM-based Continuous Intrusion Detection Framework for Next-Gen Networks [0.7100520098029439]
  The framework employs a transformer encoder architecture, which captures hidden patterns in a bidirectional manner to differentiate between malicious and legitimate traffic. The system incrementally identifies unknown attack types by leveraging a Gaussian Mixture Model (GMM) to cluster features derived from high-dimensional BERT embeddings. Even after integrating additional unknown attack clusters, the framework continues to perform at a high level, achieving 95.6% in both classification accuracy and recall.
  arXiv  Detail & Related papers  (2024-11-04T18:12:14Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids [53.2306792009435]
  FaultGuard is the first framework for fault type and zone classification resilient to adversarial attacks. We propose a low-complexity fault prediction model and an online adversarial training technique to enhance robustness. Our model outclasses the state-of-the-art for resilient fault prediction benchmarking, with an accuracy of up to 0.958.
  arXiv  Detail & Related papers  (2024-03-26T08:51:23Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)
• Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing [5.675436513661266]
  Crowdsensing systems are vulnerable to various attacks as they build on non-dedicated and ubiquitous properties. Previous works suggest that GAN-based attacks exhibit more crucial devastation than empirically designed attack samples. This paper aims to detect intelligently designed illegitimate sensing service requests by integrating a GAN-based model.
  arXiv  Detail & Related papers  (2022-02-16T00:23:25Z)
• SAGE: Intrusion Alert-driven Attack Graph Extractor [4.530678016396476]
  Attack graphs (AGs) are used to assess pathways availed by cyber adversaries to penetrate a network. We propose to automatically learn AGs based on actions observed through intrusion alerts, without prior expert knowledge.
  arXiv  Detail & Related papers  (2021-07-06T17:45:02Z)
• Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence [94.94833077653998]
  ThreatRaptor is a system that facilitates threat hunting in computer systems using open-source Cyber Threat Intelligence (OSCTI) It extracts structured threat behaviors from unstructured OSCTI text and uses a concise and expressive domain-specific query language, TBQL, to hunt for malicious system activities. Evaluations on a broad set of attack cases demonstrate the accuracy and efficiency of ThreatRaptor in practical threat hunting.
  arXiv  Detail & Related papers  (2020-10-26T14:54:01Z)

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.