LLMs for Cybersecurity

LLM: Large Language Model

Ask about this topic

Overview

This field studies how large language models can help identify and explain vulnerabilities, interpret threat intelligence and security logs, and support tasks such as incident response and penetration testing. Common approaches include retrieval-augmented generation, cybersecurity domain adaptation, multi-agent workflows, and integration with static analysis, command-line tools, fuzzers, or execution-based verification. Evaluation spans code datasets, CTI and log benchmarks, and interactive cyber ranges, where results often depend on data quality, tool access, prompts, and scoring methods. Models can assist with specific tasks, but unreliable reasoning, weak generalization to real systems, and the dual-use risks of offensive capability remain central challenges.

Latest papers

CardsList

258 papers32 papers in the last four weeks, up 52% on the four weeks before. 0.2% of all new papers.

  1. Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

    Apr 8, 2026Zi Liang, Qipeng Xie, Jun He +7Software Vulnerability DetectionSoftware Security

    The Hong Kong Polytechnic University · HKUST · SF Express +1

  2. CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

    Apr 7, 2026Gustav Keppler, Moritz Gstür, Veit HagenmeyerIndustrial Control System SecurityLLM Agent Evaluation

    Karlsruhe Institute of Technology (KIT)

  3. Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

    Apr 7, 2026Jiaren Peng, Zeqin Li, Chang You +17Automated Penetration TestingLLMs for Cybersecurity

    School of Cyber Science and Engineering, Sichuan University, China · Institute for Network Sciences and Cyberspace, Tsinghua University, China · National University of Singapore, Singapore +4

  4. From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems

    Apr 7, 2026Shaofei Huang, Christopher M. Poskitt, Lwin Khin SharCybersecurityCPS Security

    Singapore Management University, Singapore

  5. Towards the Development of an LLM-Based Methodology for Automated Security Profiling in Compliance with Ukrainian Cybersecurity Regulations

    Apr 7, 2026Daniil Shafranskyi, Iryna Stopochkina, Mykola IlinCybersecurityLLMs for Cybersecurity

    National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi Ave, 37, Kyiv, 03056, Ukraine

  6. LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations

    Apr 7, 2026Anes Abdennebi, Nadjia Kara, Laaziz Lahlou +1CybersecurityLLMs for Cybersecurity

    Department of Software Engineering and IT, École de Technologie Supérieure (ÉTS), Montreal, Canada · Department of Mathematics & Computer Science, UQTR, Trois-Rivières, Canada

  7. Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models

    Apr 7, 2026Umesh Biswas, Shafqat Hasan, Syed Mohammed Farhan +2Explainable Intrusion DetectionLLMs for Cybersecurity

    Computer Science & Engineering, Mississippi State University

  8. Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework

    Apr 6, 2026Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen +2Structured PromptingCoT Reasoning

    Department of Computing, University of Turku, 20014 Turku, Finland

  9. Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

    Apr 5, 2026Dalal Alharthi, Ivan Roberto Kawaminami GarciaCybersecurityDigital Forensics

    University of Arizona, Tucson, AZ, USA

  10. CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

    Apr 4, 2026Baicheng Chen, Yu Wang, Ziheng Zhou +4Software Reverse EngineeringLLMs for Cybersecurity

    Shanghai Qi Zhi Institute · The Chinese University of Hong Kong, Shenzhen · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +4

  11. AICCE: AI Driven Compliance Checker Engine

    Apr 3, 2026Mohammad Wali Ur Rahman, Martin Manuel Lopez, Lamia Tasnim Mim +4LLMs for Cybersecurity

    Department of Electrical and Computer Engineering from the University of Arizona, Tucson, AZ 85721, USA. · Avirtek, Inc., Tucson, AZ 85712, USA. · Joint Interoperability Test Command (JITC), United States Department of Defense, AZ 85613, USA.

  12. Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models

    Apr 2, 2026Samita Bai, Hamed Jelodar, Tochukwu Emmanuel Nwankwo +4Malware ClassificationLanguage Model Ensembles

    Canadian Institute for Cybersecurity, Faculty of Computer Science, University of New Brunswick, Fredericton, Canada.

  13. RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

    Apr 2, 2026Ayush Garg, Sophia Hager, Jacob Montiel +5Software Vulnerability DetectionLLMs for Cybersecurity

    USA · Johns Hopkins University, USA · Amazon Web Services, USA

  14. Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection

    Apr 2, 2026Subho Halder, Siddharth Saxena, Kashinath Kadaba Shrish +1LLMs for CybersecuritySoftware Vulnerability Detection

    Mattersec Labs · Kalmantic Labs

  15. The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities

    Mar 26, 2026Ron LitvakPhishing DetectionLLM Agent Security

    Independent Researcher, Columbia University

  16. Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

    Mar 25, 2026Michael Somma, Markus Großpointner, Paul Zabalegui +2Automated Penetration TestingLLMs for Cybersecurity

    JOANNEUM RESEARCH Forschungsgesellschaft mbH, DIGITAL – Institute for Digital Technologies, Steyrergasse 17, 8010 Graz, Austria · TU Graz, Institute for Technical Informatics, Inffeldgasse 16/I, 8010 Graz, Austria · Alias Robotics S.L., Calle Venta de la Estrella, 6 Pab. 130, 01006 Vitoria-Gasteiz, Álava, Spain +1

  17. Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations

    Mar 25, 2026Ziyin Zhou, Jianyi Zhang, Xu ji +3Knowledge Conflicts in Language ModelsLLMs for Cybersecurity

    Beijing Electronic Science and Technology Institute

  18. STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving

    Mar 23, 2026James Hugglestone, Samuel Jacob Chacko, Dawson Stoller +2LLMs for CybersecurityLLM Agents

    Department of Computer Science, Florida State University, Tallahassee, USA

  19. OrgForge-IT: A Verifiable Synthetic Benchmark for LLM-Based Insider Threat Detection

    Mar 23, 2026Jeffrey FlyntLLMs for CybersecuritySynthetic Benchmark Generation

    Independent Researcher

  20. AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing

    Mar 21, 2026Sen Fang, Weiyuan Ding, Zhezhen Cao +2Software Vulnerability DetectionLLMs for Cybersecurity

    NC State University · University of Alberta

  21. An Agentic Multi-Agent Architecture for Cybersecurity Risk Management

    Mar 20, 2026Ravish Gupta, Saket Kumar, Shreeya Sharma +2CybersecurityAI Risk Management

    BigCommerce · Lead Software Engineer, BigCommerce; IEEE Senior Member · University at Buffalo, The State University of New York, Buffalo, NY, USA +4

  22. Implicit Patterns in LLM-Based Binary Analysis

    Mar 19, 2026Qiang Li, XiangRui Zhang, Haining WangLLMs for CybersecurityImplicit Reasoning in Language Models

    Beijing Jiaotong University China · Virginia Tech USA

  23. An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation

    Mar 17, 2026Kushankur Ghosh, Mehar Klair, Kian Kyars +2Data ProvenanceAnomaly Detection

    University of Alberta

  24. Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios

    Mar 11, 2026Linus Folkerts, Will Payne, Simon Inman +11LLMs for CybersecurityAI Agent Evaluation

    AI Security Institute, United Kingdom.

  25. VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection

    Mar 11, 2026Renwei Meng, Haoyi Wu, Jingming WangSoftware Vulnerability DetectionAI Agent Auditing

  26. Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

    Mar 6, 2026Ondřej Lukáš, Jihoon Shin, Emilia Rivas +6Generalization in RLAI Agent Evaluation

    Czech Technical University in Prague (CTU) · University of Texas at El Paso (UTEP) · Universidad Nacional de Cuyo (UNCUYO)

  27. SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection

    Mar 5, 2026Touseef Hasan, Blessing Airehenbuwa, Nitin Pundir +2LLMs for CybersecurityRetrieval-Augmented Generation

    School of Computing, Wichita State University · Department of Electrical and Computer Engineering, Auburn University · IBM

  28. CAM-LDS: Cyber Attack Manifestations for Automatic Interpretation of System Logs and Security Alerts

    Mar 4, 2026Max Landauer, Wolfgang Hotwagner, Thorina Boenke +2CybersecurityLLMs for Cybersecurity

    Austrian Institute of Technology, Center for Digital Safety & Security, Vienna, 1210, Austria

  29. ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

    Mar 2, 2026Nancy Lau, Louis Sloot, Jyoutir Raj +6AI Agent Security BenchmarksLLMs for Cybersecurity

    UC Santa Cruz · Carnegie Mellon University · Independent +2

  30. Quantifying Frontier LLM Capabilities for Container Sandbox Escape

    Mar 1, 2026Rahul Marchand, Art O Cathain, Jerome Wynne +8LLM Safety BenchmarksLLM Agent Security

    University of Oxford · UK AI Security Institute