LLMs for Cybersecurity

LLM: Large Language Model

Ask about this topic

Momentum

19 papers in the last four weeks, up 280% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 166

All topics
CardsList

  1. Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

    Jul 3, 2026Eduardo Almeida Palmieri, Mohamed Chahine Ghanem, Dipo Dunsin +3LLM Agent EvaluationLLMs for Cybersecurity

    School of Computer Science and Mathematics, Keele University, Newcastle-under-Lyme ST5 5AA, U.K. · Cybersecurity Institute, University of Liverpool, Liverpool L69 3BX, U.K. · Department of Applied Computing IICL, University of Wales Trinity Saint David, London E14 4HA, U.K. +2

  2. Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI

    Jul 3, 2026Romain Gerard, Assmaa Zeghaider, Yan GuoLLM Agent OrchestrationLLM Agent Evaluation

    University of Science and Technology of China, Hefei, China · Suzhou Institute for Advanced Research, University of Science and Technology of China

  3. JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode

    Jul 2, 2026Norbert Sandor Szolnoki, Gabor AntalSoftware Vulnerability DetectionLLMs for Cybersecurity

    University Of Szeged Szeged, Hungary

  4. Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

    Jul 2, 2026Vadym Hadetskyi, Dario Pasquini, Artem SorokinLLM RefusalLLM Safety Alignment

    Cracken AI

  5. AI-Generated PowerShell Malware: An Experimental Framework and Dataset

    Jun 29, 2026Luciano Pianese, Vittorio Orbinato, Pietro Liguori +1LLMs for CybersecurityMalware Analysis

    Department of Electrical Engineering and Information Technology (DIETI), Universit`a degli Studi di Napoli Federico II, Naples, Italy · Gran Sasso Science Institute, L’Aquila, Italy

  6. COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies

    Jun 29, 2026Chen Frydman, Aviram Zilberman, Rubin Krief +6Autonomous Cyber DefenseCybersecurity

    Ben-Gurion University of The Negev, Beer Sheva, Israel · Jerusalem College of Technology, Jerusalem, Israel · Fujitsu

  7. Cybersecurity is the True Frontier for Generative AI Success or Failure

    Jun 27, 2026Edward Raff, Maor Ashkenazi, Sagar Samtani +2CybersecurityLLMs for Cybersecurity

    CrowdStrike · University of Maryland, Baltimore County · Edward Raff∗† +2

  8. Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs

    Jun 26, 2026Cristhian Kapelinski, Diego KreutzPrivacy-Preserving Language ModelsMemorization in Language Models

    Federal University of Pampa (UNIPAMPA), Alegrete, Brazil

  9. LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity

    Jun 26, 2026Yiwei Xu, Yong Zhuang, Xuanming Liu +6Autonomous Cyber DefenseLLM Agent Security

    School of Cyber Science and Engineering, Wuhan University, Wuhan, China. · Department of Computer Science and Engineering, University at Buffalo, Buffalo, USA.

  10. Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

    Jun 25, 2026Ryan FettermanAdversarial AttacksLLM Fine-Tuning

    Cisco Talos

  11. Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study

    Jun 24, 2026Giulian Biolo, Michael Tezza, Yuanjun Gong +1Automated Program RepairHuman-in-the-Loop Evaluation

    University of Trento, IT · Vrije Universiteit Amsterdam, NL

  12. An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz

    Jun 24, 2026Lea Roxanne Muth, Marian MargrafCybersecurityLLMs for Cybersecurity

    Department of Mathematics and Computer Science Freie Universität Berlin Berlin, Germany

  13. Leveraging Large Language Models to Obscure Code Stylometry: A Comparative Study of GPT-3.5 and GPT-4

    Jun 21, 2026Saman Pordanesh, Benjamin TanStylometryAuthorship Attribution

  14. Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases

    Jun 20, 2026Yiwei Hou, Hao Wang, Muxi Lyu +6Software Vulnerability DetectionCybersecurity

    University of California, Berkeley

  15. CNnotator: LLM-Guided Memory Safety Annotation Synthesis

    Jun 20, 2026Twain Byrnes, Mike DoddsLLM-Assisted AnnotationProgram Synthesis

    Carnegie Mellon University Pittsburgh, PA, USA · Galois, Inc. Portland, OR, USA

  16. Evaluating LLMs for Real-World Web Vulnerability Detection

    Jun 19, 2026Sebastian Neef, Luca Jungnickel, Antonio Benjamin Buchholz +2Software Vulnerability DetectionLLM Reliability

    Technische Universität Berlin, Einsteinufer 17, 10587 Berlin, Germany · Freie Universität Berlin, Kaiserswerther Str. 16-18, 14195 Berlin, Germany

  17. Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers

    Jun 19, 2026Kerri Prinos, Lilianne Brush, Cameron DentonCybersecurityAI Agent Security

    Horizon3.ai, San Francisco, CA, 94111, USA

  18. Can LLMs Reason About Brand Ownership? An Empirical Study of Domain Attribution Intelligence

    Jun 18, 2026Fathima Mashood, Mohamed NabeelLLM EvaluationLLM Reliability

  19. Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

    Jun 18, 2026Arastoo Zibaeirad, Marco VieiraLLM EvaluationSoftware Vulnerability Detection

    University of North Carolina at Charlotte, Charlotte, NC, USA

  20. Multi-View Decompilation for LLM-Based Malware Classification

    Jun 18, 2026Bercan Turkmen, Vyas RainaSoftware Reverse EngineeringLLM Prompting

    Independent Researcher · SPARK

  21. Secure Coding Drift in LLM-Assisted Post-Quantum Cryptography Development: A Gamified Fix

    Jun 17, 2026R. D. N. Shakya, C. P. Wijesiriwardana, S. M. Vidanagamachchi +1LLMs for CybersecuritySecure Code Generation

    University of Moratuwa Sri-Lanka, Moratuwa · University of Ruhuna Sri-Lanka, Matara · RMIT University Australia, Melbourne

  22. OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

    Jun 17, 2026Nahum Korda, Gadi EvronSoftware Vulnerability DetectionStatic Code Analysis

    Knostic

  23. Code-Augur: Agentic Vulnerability Detection via Specification Inference

    Jun 17, 2026Zhengxiong Luo, Mehtab Zafar, Dylan Wolff +1Automated Software TestingSoftware Vulnerability Detection

    National University of Singapore

  24. Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports

    Jun 16, 2026Ahmed Ryan, Saad Sakib Noor, Md Erfan +3LLM EvaluationCyber Threat Intelligence

    The University of Alabama · The University of Dhaka

  25. Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond

    Jun 16, 2026Hobin Kim, Xiaoyuan Wu, Omer Akgul +2LLM AuditingLLM Reliability

    Carnegie Mellon University · RSAC Labs

  26. Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

    Jun 13, 2026Yiwei Chen, Lichi Li, Kai Cheung +2LLM EvaluationLLM Fine-Tuning

    Cisco Systems, Inc., San Francisco, CA, USA · Michigan State University, East Lansing, MI, USA

  27. AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

    Jun 12, 2026Fengyu Liu, Jiarun Dai, Yihe Fan +11CybersecurityAI Agent Security Benchmarks

    Fudan University

  28. The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

    Jun 11, 2026Jiaqi Luo, Jiarun Dai, Zhile Chen +8LLM EvaluationAI Agent Security Benchmarks

    Fudan University · Shanghai Artificial Intelligence Laboratory · Concordia AI +1

  29. Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

    Jun 10, 2026Derek Yohn, Luke Flancher, Mirajul Islam +1Software Vulnerability DetectionLLM Agent Evaluation

    College of Engineering and Science, Florida Institute of Technology, Melbourne, Florida, USA

  30. Do LLMs Make Neural Distinguishers Wise?

    Jun 9, 2026Tatsuya Sakagami, Masashi Hisai, Naoto YanaiLLMs for CybersecurityPrompt Engineering

    Panasonic Holdings Corporation 1006 Kadoma, Kadoma City, Osaka

  31. Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations

    Jun 9, 2026Aniket Anand, Yiwei Hou, Daniel Fields +4LLM EvaluationCybersecurity

    University of Chicago · USA · University of California, Berkeley +1

  32. SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection

    Jun 6, 2026Yichen Chen, Siying Li, Yuhang Liang +2Multi-Agent LLM SystemsFinancial Fraud Detection

    National University of Singapore · School of Computing, Singapore 117417 · University of Chinese Academy of Sciences +4

  33. GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks

    Jun 4, 2026Hassan Jalil Hadi, Rehana Yasmin, Ali ShokerNetwork Intrusion DetectionSynthetic Benchmark Generation

    Cyber Security and Resilience Technology (CyberSaR), King Abdullah University of Science and Technology (KAUST), Saudi Arabia

  34. ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense

    Jun 4, 2026Anlan Zheng, Tiantian ZhuAI Agent Security BenchmarksAutomated Penetration Testing

    Zhejiang University of Technology Hangzhou, China

  35. Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

    Jun 3, 2026Cristina Carleo, Pietro Liguori, Naghmeh Ivaki +1LLM Safety AlignmentLLMs for Cybersecurity

    University of Naples Federico II, Naples, Italy · University of Coimbra, CISUC/LASI, Coimbra, Portugal · University of North Carolina at Charlotte, Charlotte, NC, USA

  36. Large Byte Model: Teaching Language Models About Compiled Code

    Jun 1, 2026Florian Störtz, Catalin-Andrei Stan, Alexandru Dinu +4Malware ClassificationByte-Level Language Model

    CrowdStrike · CrowdStrike U.K. · CrowdStrike Romania +1

  37. IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems

    Jun 1, 2026Yuchen Zhang, Ning Xi, Pengbin Feng +5Cyber-Physical SystemsIndustrial Anomaly Detection

    School of Cyber Engineering, Xidian University, Xi’an 710126, China · School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC, Australia · School of Computer Science and Technology, Xidian University, Xi’an 710126, China

  38. Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research

    May 31, 2026Michael J. BommaritoSoftware SecurityLLMs for Cybersecurity

  39. A New Framework for Cybersecurity Refusals in AI Agents

    May 31, 2026Eliot Krzysztof Jones, Mateusz Dziemian, Matt Fredrikson +1LLM Agent EvaluationLLM Refusal Behavior

    Work done while at Gray Swan · Gray Swan AI · Carnegie Mellon University

  40. A Protocol-Language Model for Network Intrusion (Without Deep Packet Inspection)

    May 29, 2026Vivek Kumar SharmaNetwork Intrusion DetectionEncrypted Network Traffic Analysis

    Palo Alto Networks

  41. How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

    May 28, 2026Galip Tolga ErdemAutomated Penetration TestingLLMs for Cybersecurity

    Independent Researcher

  42. Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

    May 28, 2026Mark Vero, Fabian Kaczmarczyck, Ivan Petrov +6LLMs for Cybersecurity

    1ETH Zurich · 2Google · 3Google DeepMind +2

  43. Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection

    May 28, 2026Syafiq Al Atiiq, Chun Zhou, Christian GehrmannLLM InterpretabilitySoftware Vulnerability Detection

    Lund University Lund, Sweden

  44. Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieval-Augmented Generation and Large Language Models

    May 25, 2026Mohammed N. Swileh, Shengli Zhang, Kai LeiNetwork Intrusion DetectionCybersecurity

    College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China · ICNLab, Shenzhen Graduate School, Peking University, Shenzhen, People’s Republic of China

  45. CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly

    May 25, 2026Yihe Fan, Changyi Li, Lichen Xu +4LLM Agent Self-ImprovementAutomated Penetration Testing

    Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Shanghai Pudong Research Institute of Cryptology

  46. TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

    May 25, 2026Yutong Cheng, Changze Li, Raihan Sultan Pasha Basuki +3Cyber Threat IntelligenceDocument Information Extraction

    Virginia Tech · Universitas Ary Ginanjar, Jakarta, Indonesia · Amazon

  47. APT-Agent: Automated Penetration Testing using Large Language Models

    May 24, 2026William Guanting Li, Alsharif Abuadbba, Kristen Moore +1LLM Hallucination MitigationAutomated Penetration Testing

    University of Queensland · University of Queensland Brisbane, Australia · CSIRO Data61 +2

  48. CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering

    May 23, 2026Matilda Gaddi, Jin Noh, Onat Gungor +1CybersecurityLLMs for Cybersecurity

    Department of Computer Science and Engineering University of California, San Diego (UCSD)

  49. Demystifying the Mythos or Disrupting Bugonomics? From Zero-Day Asymmetry to Defender Remediation Throughput

    May 23, 2026Alfredo Pesoli, Herman Errico, Lorenzo CavallaroSoftware Vulnerability DetectionSoftware Security

    Bynario · Vanta · University College London / Bynario

  50. Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content

    May 23, 2026Rohan Pandey, Archit BhujangIndirect Prompt InjectionLLMs for Cybersecurity

    DigitalOcean · Arizona State University

  51. Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

    May 22, 2026Vivek Dahiya, Sunny Nehra, Vipul Dholariya +2Software Vulnerability DetectionCybersecurity

  52. HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection

    May 20, 2026Danyu Sun, Jinghuai Zhang, Yuan Tian +1LLM EvaluationCybersecurity

    University of California, Irvine · University of California, Los Angeles

  53. PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents

    May 20, 2026Sidnei Barbieri, Ágney Lopes Roth Ferraz, Lourenço Alves Pereira JúniorAutonomous Cyber DefenseLLM Agent Security

    Aeronautics Institute of Technology (ITA), São José dos Campos/SP, Brazil

  54. GenAI-Driven Threat Detection with Microsoft Security Copilot

    May 20, 2026Scott Freitas, Amir GharibAutonomous Cyber DefenseCybersecurity

    Microsoft Security Research

  55. Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System

    May 19, 2026Ivan DobrovolskyiLLM Fine-TuningText Classification

    MS in AI & ML Engineering, Independent Researcher, Sunnyvale, CA, USA

  56. Measuring Safety Alignment Effects in Autonomous Security Agents

    May 19, 2026Isaac David, Arthur GervaisLanguage Model Safety EvaluationLLM Safety Alignment

    University College London

  57. Benchmarking Mythos-Linked Bug Rediscovery

    May 17, 2026Isaac David, Arthur GervaisSoftware EngineeringSoftware Vulnerability Detection

    University College London

  58. Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications

    May 17, 2026Isaac David, Arthur GervaisLanguage Model Safety EvaluationCybersecurity

    University College London

  59. GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction

    May 15, 2026Liangyi Huang, Zichen Liu, Fei Shao +5KG ConstructionCyber Threat Intelligence

    Arizona State University · Case Western Reserve University · University of Notre Dame +2

  60. Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

    May 15, 2026Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3Multi-Agent LLM SystemsLLM Agent Orchestration

    Carleton University Ottawa, Ontario, Canada · Defence R&D Canada Ottawa, Ontario, Canada · Cistel Technology Ottawa, Ontario, Canada