Large Language Models for Cyber Security: A Systematic Literature Review

Cited by (191)

Items 101–191 of 191

1. Retrieval-Augmented LLMs for Security Incident Analysis
   Xavier F. Cadet, Aditya Vikram Singh, Harsh Mamania, Edward Koh, Alex Fitts, Dirk Van Bruggen, Simona Boboila, Peter S. Chin, Alina Oprea · 2026 · ACM Conference on AI and Agentic Systems (CAIS)
2. Evaluating Retrieval-Augmented Generation for Small Language Models in Cybersecurity Education
   Hitesh Kumar, Nishtha Hooda · 2026 · International Conference on Computing for Sustainable Global Development
3. A Privacy-Preserving Framework for Cyber Incident Analysis from Network Packets Using +Large Language Models
   Md Naeemur Rahman, Mohammad Tahir, Jouni Isoaho, Seppo Virtanen · 2026 · IEEE Conference on Artificial Intelligence (CAI)
4. GLITCH_AI: A Hybrid Framework for Automated Penetration Testing with LLM-Driven Adaptation and Reporting
   Maria Gonzalez Herrero, Amit Kumar Singh, Zeba Khanam · 2026 · IEEE Conference on Artificial Intelligence (CAI)
5. Construction of a Retrieval-Augmented LLM Agent for Health Education and a Multi-dimensional Evaluation Framework: A Comparative Study of Chinese Large Language Models
   Jinglong Chen, Dan Wang, Yao Hu, Qun Yuan, Lin Lin, Ying Zhang · 2026 · International Conference on Big Data and Informatization Education (ICBDIE)
6. TeleHunt: A Framework and Tool for Efficient Cybercriminal Community Discovery on Telegram
   Roy Ricaldi, Victor Asanache, Luca Allodi · 2026 · Lecture notes in computer science
7. Secure, Smart, Automated, and Privacy-Preserving Cybersecurity Policy Compliance Framework for Sensitive Data Protection
   Jemima Owusu-Tweneboah, Amani Altarawneh · 2026 · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC)
8. Agentic Architecture for Formalising Security Risk Elicitation
   Vjatšeslav Antipenko, Raimundas Matulevičius · 2026 · Lecture notes in business information processing
9. Cyber Resilience Through LLM-Enhanced Vulnerability Reports
   Mario Hoffmann, Erik Buchmann · 2026 · Communications in computer and information science
10. PenExpert: A multi-agent hybrid LLM–expert system framework for autonomous penetration testing
    Zhi Li, Tianyang Zhou, Junhu Zhu, Dongyang Li, Xiaodong Zhu, Dongze Wei, Jinghu Liu, Mengbo Song · 2026 · Expert Systems with Applications
11. AnonShield: Scalable On-Premise Pseudonymization for CSIRT Network Vulnerability Data
    Cristhian Kapelinski, Douglas Paim Lautert, Beatriz Machado, Diego Kreutz, Isadora Garcia Ferrão · 2026 · Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC)
12. Cognitive Network Intrusion Detection Systems: Anomaly and Malware Detection for Zero-Day Attack Resilience
    Jimmy Agung Gunawan, Moses Laksono Singgih, Raden Venantius Hari Ginardi · 2026 · Network
13. Risk management for cyber insurance: a survey for data-driven approaches with the use of AI
    Antonios Paragioudakis, Nikos Komninos, Michail Smyrlis, Georgios Spanoudakis, Christos Kloukinas Z · 2026 · International Journal of Information Security
14. AI-Assisted Cybersecurity Mesh for Threat Detection in Edge-Enabled Communication Networks
    Utham Kumar Anugula Sethupathy, Vijayanand Ananthanarayanan · 2026 · International Journal of Communications Network and System Sciences
15. A Multi-Stage AI Framework for Intelligent Incident Detection and Response Automation in Security Operations Centers
    Mina Adel, Aboulela Abdo, doaa sayed, reham darwish, Omar Moataz · 2026 · Journal of Smart Algorithms and Applications (JSAA)
16. Origin Story: A Comprehensive Lifecycle Analysis of Same-Origin Policy Bugs
    Jakub Szymsza, Gertjan Franken, Vik Vanderlinden, Tom Van Goethem, Mathy Vanhoef, Lieven Desmet · 2026 · IEEE Secure Development Conference (SecDev)
17. Knowledge-Driven Autonomous Defense in CPNs through a Hierarchical Collaborative Framework
    Yue Wang, X Wang, Tao Xiong, Hao Lu, Yue Kou · 2026 · International Conference on Computer Supported Cooperative Work in Design (CSCWD)
18. Cross-model evaluation of phishing detectors against LLM-generated emails
    Rommel Gutierrez, William Eduardo Villegas-Ch, Jaime Govea · 2026 · Frontiers in Big Data
19. LangGraph-Orchestrated NL2SQL: Combining PII Anonymization with Deterministic SQL Validation
    Valli Gayatri P, Obana Pujar, Meghana Kiranchand, Kavana P R, P K Udayaprasad · 2026 · International Conference on System, Computation, Automation and Networking (ICSCAN)
20. BabeLLM: A unified taxonomy for NLP-based LLM cybersecurity applications
    Pellegrino Casoria, Simon Pietro Romano · 2026 · Expert Systems with Applications
21. Parameter-Efficient Mixture-of-Experts Adaptation of Qwen3 for Cross-Site Scripting Detection
    Yuancheng Zhao, Haohang Ke, Juan Guo, Yueguo Ma, Beihan Huang, Fangjie Liu · 2026 · International Conference on Electronic Engineering and Information Systems (EEISS)
22. A Multimodal Large Language Model Approach for Automated Security Requirements Verification
    Ismail Esack Dawoodjee, Assadarat Khurat, Thanapon Noraset · 2026 · International Joint Conference on Computer Science and Software Engineering
23. SCALA-NIDS: Safety-constrained LLM-Advised closed-loop adaptation for online open-world network intrusion detection
    Xiaojie Qin, Qingjun Yuan, Haopeng Fan, Jing Tao, Pinghui Wang, Jihong Teng, Siqi Lu, Yongjuan Wang · 2026 · Expert Systems with Applications
24. Ensemble Deep Learning for Robust Prompt Injection Detection in Banking LLMs
    Neha Manoj, Deepak S G, Turala Pranav, Devi Rajeev · 2026 · International Conference on Secure Cyber Computing and Communications (ICSCCC)
25. Intelligence Augmentation in a Platform for Cyber Situational Awareness
    Lukáš Sadlek, Milan Boháček, Jan Rolínek, Martin Husák · 2026 · IEEE International Conference on Network Softwarization (NetSoft)
26. AI-Powered Cyber Threat Intelligence Analyst Platform for Automated Vulnerability Assessment and Threat Analysis
    Tikkireddi Aditya Kumar, K. Deepak, P Sai Vignesh, Sayeed Rahman, Sri Vathsav Reddy, Navadeep Garidepally · 2026 · International Conference on Innovations in Cybersecurity and Data Science (ICICDS)
27. IA-VulD: LLM-based Web Vulnerability Attack Detection via Instruction-Aware Embedding
    Juxin Xiao, Xiao Wang, Jin Zhao, B Liu, Xingchen Chen, Jie Yin, Qixu Liu · 2026 · Lecture notes in computer science
28. On Targeted Output Generation via Adversarial Reframing in Language Models
    Shahnewaz Karim Sakib, Swati Kar, Anindya Bijoy Das · 2026 · Lecture notes in computer science
29. LLM-Based Intrusion and Anomaly Detection for IoT Networks: A Systematic Survey
    S. Vítek · 2026 · IEEE Internet of Things Journal
30. Mapping the Research Landscape of Large Language Models in Network Intrusion Detection
    Recep Arslan, Turgut Özseven · 2026 · International Symposium on AI-Driven Engineering Systems (ISADES)
31. From Scripts to Prompts: How Large Language Models Are Transforming Penetration Testing
    Eman M. Alatawi, Umar Albalawi · 2026 · IEEE International Conference on AI and Data Analytics (ICAD)
32. Hierarchical multi-agent AI framework for cybersecurity in cyber–physical systems
    Antonino Ferraro, Antonio Galli, Vincenzo Moscato, Gian Marco Orlando, Diego Russo · 2026 · Computer Networks
33. Large Language Model-Driven Cybersecurity Threat Detection and Intelligent Analysis
    Sheng Xu · 2026 · International Conference on Computer Intelligence and Software Engineering (CICSE)
34. RAPID: A Resource-Aware Prompt Injection Defense for LLM-Enabled Threat Detection
    Ebuka Chinaechetam Nkoro, Wei Yu, Weixian Liao · 2026 · IEEE Internet of Things Journal
35. Large Language Models in the Crosshairs: A Systematic Review of Modern Cybersecurity Challenges and Applications
    Alison Betancourt, GINO ALESSANDRO AUZ COYAGO, Kelly Sangoluisa, Marcel Auz-Torres, Sang Guun Yoo · 2026 · IEEE Access
36. Adversarial resilience in cloud based machine learning: a unified framework for robust threat detection and forecasting
    Ayaan Sehgal, Vedant Vijay Zade, K. Pooja Karan, Monami Som Saha, Bhawana Tyagi · 2026 · Journal of Cloud Computing Advances Systems and Applications
37. AI-Enabled Technical Exposure Risk (ATER): From Public Technical Disclosures to Exposure Intelligence for Cybersecurity Resilience
    Natalija Parlov, Riko Luša, Gordan Akrap · 2026 · Future Internet
38. Cyber Response Automation with Dedicated AI Agents
    Stanimir Ivanov Kabaivanov, Veneta Markovska · 2026 · International Scientific Conference TechSys — Engineering, Technology and Systems (TechSys)
39. Smishing Attacks: A Survey and Taxonomy of Threats, Detection Methods and Mitigation Strategies
    Ayşe Sayın, Mehmet Tahir Sandıkkaya · 2026 · SN Computer Science
40. A Four-Axis Systematization of AI and Cybersecurity in the Era of Large Language Models
    Mashiat Amin Farin, Bhavani M. Thuraisingham · 2026 · IEEE Conference on Big Data Security on Cloud (BigDataSecurity)
41. Assessing Zero-Day Attack Threat Levels by Monitoring Embedded Code-Change in Web Browsers
    Funke Ajayi, Atef Mohamed Shalan · 2026 · International Conference on Artificial Intelligence, Robotics and Control (AIRC)
42. Trustworthy and Temporally Robust Web Attack Detection for Autonomous Edge Network Security
    Jincheng Deng, Binran Liu, Zhifei Liao, Zhongyou Ren, Zhekai Du, Yuan Zhang, Jingjing Li · 2026 · IEEE Transactions on Network Science and Engineering
43. Artificial Intelligence for Cybersecurity: A Scoping Survey of Paradigms, Applications, and Emerging Trends
    Amitabh Mishra, Vasudha Vedula, Asmi Mishra, Shrishti Sharma · 2026 · Algorithms
44. Threat Actor Attribution Applying a Tactics–Techniques–Procedures Approach: An Empirical Investigation
    Shaheen Hussain, Krassie Petrova · 2026 · Future Internet
45. Interpretable Artificial Intelligence Models Based on Large Language Models for Web Application Vulnerability Detection and Security Analysis
    Ilya Shelestov, Aliya Kanatova, Neilya Yessentay, Gulnara Santayevna Zhetessova · 2026 · International Conference on Cybersecurity, Digital Forensics, and AI Applications (ICCSDFAI)
46. AI as a tool for cyber attacks
    Gulnur Shuteyeva, Zukhra Sarsenbi, Saltanat Umbetalina, Aldiyar Kaldybek · 2026 · International Conference on Cybersecurity, Digital Forensics, and AI Applications (ICCSDFAI)
47. Evaluating Robustness of Manifest-Based Malware Detection Methods for Android OS
    Szymon Tokarski, Paweł Moszczyński, Wojciech Mazurczyk · 2026 · Lecture notes in computer science
48. A Methodology for Automatic Test Case Generation in Intelligent Connected Vehicle Cybersecurity Testing Based on Large Language Models
    Qianchuang Zhi, Zhen Guo, Qi Yu, Mingming Yu, Longhai Yu, Shixuan Ren · 2026 · IEEE International Conference on Electronics, Energy Systems and Power Engineering (EESPE)
49. CriticIDS: LLM-Augmented Intrusion Detection with AutoML and Explainability for IoT Networks
    Tasnimul Hasan, Samia Tasnim · 2026 · IEEE Annual International Computer Software and Applications Conference (COMPSAC)
50. Human vs. LLM Risk Assessment: A Comparative Study of ISO 27001 Cyber Risk Classification
    Marek Hrabčák, Zoltán Balogh · 2026 · EAI/Springer Innovations in Communication and Computing
51. HGFuzzer: Directed Greybox Fuzzing via Large Language Model
    Hanxiang Xu, Yanjie Zhao, Junqing Yu, Haoyu Wang · 2026 · ACM Transactions on Software Engineering and Methodology
52. Large Language Models for Fuzz Testing in Microservices: A Systematic Literature Review
    Ying Song, Ke Ping, Yuqing Wang, Xiaozhou Li · 2026 · Lecture notes in computer science
53. Benchmarking Large Language Models for Binary Function Name Prediction
    Yunxiang Ge, Bing Xia, Yong Ding, Wenbo Liu · 2026 · ENGINEERING Information Technology & Electronic Engineering
54. An Integrated Honeypot and LLM-Based Framework for near Real-Time Detection and Behavioral Analysis of Malicious Activities
    Rúben S. Oliveira, Tiago F. N. Gomes, Daniel Pinho, Fernando Luís Almeida · 2026 · Journal of Cybersecurity and Privacy
55. Performance Evaluation of LLMs for Generating and Enriching Application Behavioural Automata
    Katsuki Isobe, Aristide Urli, Nicolas Schnepf, Rémi Badonnel · 2026 · IEEE/IFIP Network Operations and Management Symposium (NOMS)
56. Experimental Prompt Engineering Using Structured Language Refinement for Attack Path Analysis
    Jarrod Villareal, Mark G. Reith, Richard Ott, Christine M. Schubert Kabban · 2026 · IEEE National Aerospace and Electronics Conference (NAECON)
57. TIGER: An Open-Source Cyber-Threat Intelligence Game Environment for Reinforcement Learning
    Jesús Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen‐Porisini · 2026 · IEEE Transactions on Network and Service Management
58. A Multi-World Collaborative Approach for Evolutionary Analysis of APT Attack Behaviors
    Binhui Tang, Yishan Lu, Caiyun Li · 2026 · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA)
59. When Will the Next Attack Start? Calibrated Time-Window Prediction Using Multi-Agent LLMs
    Sandeep Kalari, Madhu Lokesh, Ravi Mukkamala · 2026 · International Conference on Intelligent Digitization of Systems and Services (IDSS)
60. Autonomous intelligence in public trust: ethical frameworks for large language models in federal cybersecurity threat hunting
    Adedamola Ajibola · 2026 · AI and Ethics
61. Large Language Models (LLMs) and Deep-Learning Frameworks as Independent Threat Actors
    Roshni Gupta, Ergashev Nuriddin Gayratovich, Gulchehra Karimova, Buriyev Javokhir, Davlatova Sayyora Toshpulatovna, Gafurov Anvar Bazarbayevich, Yakitjon Turdiyeva, Anorgul I. Ashirova · 2026 · IGI Global eBooks
62. An LLM-Augmented SIEM Architecture for Automated Incident Handling and Knowledge-Graph-Grounded False-Positive Triage
    Mohamed Elsagher, Amany Abdo, Hala Abbas · 2026 · Intelligent Methods, Systems, and Applications (IMSA)
63. Large Language Models and Agentic AI for Vulnerability Management: A Systematic Review
    Yasamin Akrami, Malek Malkawi, Reda Alhajj · 2026 · Expert Systems
64. The Security Duality of Large Language Model Agents: A Systematic Review of Self-Security Protection and Cybersecurity Empowerment
    Dasen Fu, Dalin Xiang · 2026
65. Just Old Wine in a New Bottle: Improving Vulnerability Repair Robustness to Combat Homologous but Heterogeneous Vulnerabilities
    Xin Peng, Bo Lin, Yihao Qin, Jing Wang, Xin Zhao, Xiaoling Li, Jun Ma, Xiaoguang Mao, Shangwen Wang · 2026 · Proceedings of the ACM on software engineering.
66. Beyond Similarity Scores: Evidence-Based Third-Party Library Detection for C/C++ Binaries
    Chengyue Liu, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Kaixuan Li, Yang Liu · 2026 · Proceedings of the ACM on software engineering.
67. Leveraging LLMs with Honeypots for the Security of Smart Grid SCADA Systems
    Nadia Boumkheld, Phil Legg · 2026 · Big Data and Cognitive Computing
68. LLM Comparison For Phishing Detection Using Machine Learning
    Jeremy Nicholas Ethlan Lugito, Dionysius Darren Matthew Hartono, Ventje Jeremias Lewi Engel, Muhammad Rizki Nur Majiid · 2026 · International Conference on ICT for Smart Society (ICISS)
69. TriVul: Improving Precision of Static Vulnerability Detection through Multi-agent Reasoning
    Xinye Zhao, Joanna C. S. Santos · 2026 · Lecture notes in computer science
70. Language Model-Based Cyber Threat Intelligence Systems
    Rasool Javeed Mohammad, Sujatha Lakshmi Narra, Sivasaikrishnaline Suryadevara · 2026 · International Conference on Natural Language Processing and Computer Vision (ICNPCV)
71. Explainable multi-modal Vision Transformer fusion for malware classification
    Ashwini Chikkenakoppa, C. Pavan Kumar · 2026 · Journal of Cyber Security Technology
72. Large Language Models in Cybersecurity
    Deepak Sharma, Nancy Girdhar, Ankit Modi · 2026 · Advances in computational intelligence and robotics book series
73. Deep learning-based android malware detection under realistic evaluation constraints: an architecture-centric review and reliability-aware empirical validation
    Syed Shuja Hussain, Mohd Faizal Ab Razak, Idris Ismail, Ahmad Firdaus, Abdul Azeem, Jamil Zara, Shamim Akhter · 2026 · Frontiers in Artificial Intelligence
74. FridaForge: Geração Automatizada de Scripts Frida com Contexto Dinâmico da Aplicação
    Francisco Sales, Souto Eduardo, Fernandes Horacio · 2026 · Simpósio Brasileiro de Cibersegurança (SBSeg)
75. AI-Based Real-Time Database Intrusion Detection with Secure Blockchain Audit Logging
    Lana Iqbal, Muhammad Saad Salman, Muhammed Aflah S, Prabu Selvam · 2026 · International Conference on Trends in Engineering Systems and Technologies (ICTEST)
76. VISOR: Automated Vulnerability Assessment of Software Repositories
    Negar Emami, Christian Göttel, Shuai Guo, Enrico Fregnan, Philipp Sommer, Thanikesavan Sivanthi · 2026 · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)
77. AI-Agent-Based Web Application Security Testing vs. Conventional Automated Security Testing: An Exploratory Case Study
    Krystian Kluczkiewicz, Andrzej Mycek · 2026 · Electronics
78. From Glasswing to Fable: AI-scale vulnerability discovery and the governance of selective inoculation
    Russell Lundberg · 2026 · Journal of Cyber Policy
79. A Multi-Feature Fusion Approach for Android Malware Detection Based on Prompt Engineering
    Junxiang Zhang, Daoqi Dong, Xiaomeng Wang · 2026 · International Joint Conference on Neural Networks (IJCNN)
80. ShipCrawler: Agentic Open-Source Intelligence (OSINT) Platform for Maritime Cybersecurity - Implementation and Empirical Validation
    Ahmed Nagi Nasr, Inga Zaitseva-Pärnaste, Pentti Kujala · 2026 · IEEE Access
81. THE DUAL ROLE OF LARGE LANGUAGE MODELS IN CYBERSECURITY: THREATS, DEFENSES, AND RESEARCH DIRECTIONS
    Muhammad Ali, Adnan R. Manzoor · 2026 · “ADVANCED JOURNAL OF UNIVERSITY SCIENCE AND CREATIVE INNOVATIONS” AJOU SCI
82. Avaliação de Risco usando Engenharia de Prompt em LLMs
    Arthur P. Labaki, Gustavo Roberto Pinto, Rodrigo Sanches Miani · 2026 · Simpósio Brasileiro de Cibersegurança (SBSeg)
83. Geração de Scripts Frida Guiada por Contexto Dinâmico para Análise de Segurança Android
    Francisco Sales, Souto Eduardo, Fernandes Horacio · 2026 · Simpósio Brasileiro de Cibersegurança (SBSeg)
84. Cost-Aware Confidence-Gated Two-Stage Network Intrusion Detection Under a Cross-File Cross-Class Stress Test
    Jiaming Zhang, Huishan Lai, Runtong He, Jingxue Chen, Chunhua Su · 2026 · Lecture notes in computer science
85. Cybercrime Forecasting Using Convolutional Neural Network-Long Short-Term Memory Networks
    Parin Jigishu Shah, Vishvendu Bhatt · 2026 · Cureus Journal of Computer Science.
86. RAID: Retrieval Augmented Intrusion Detection for Cyber Physical Systems
    Alberto Moccardi, Rajib Chandra Ghosh, Marcello Pelosi, Flora Amato · 2026 · Sensors
87. Evidence-Constrained Risk Interpretation for Edge IoT Security Alerts
    Ming Kang, Changzhi Wang, Yilin Zhang, Wen Chen · 2026
88. Interoperability Patterns for Semantic, Transactional, and Cognitive Agents in High-Throughput Distributed Systems: A Comprehensive Review and the STC Protocol
    Sudarshan Venkataraman · 2025 · International Journal of Computational and Experimental Science and Engineering
89. Tri-modal behavioural malware analysis: a hybrid isolation Forest–SVM–MLP framework with thirty-feature static-dynamic fusion on a contemporary six-class PE corpus
    Bikram Ghosh, Soumik Pyne, Riya Sil, Souvik Dhali · 2026 · Journal of Computer Virology and Hacking Techniques
90. The Dual-Use Nature of Large Language Models in Cybersecurity: A Bibliometric Analysis and Critical Review
    Muhammad Sharjeel Aziz, Muhammad Ali, Adnan R. Manzoor, Muhammad Younis, Zulfiya Khabirova · 2026 · Research Square
91. Governing generative AI risks: A PRISMA-ScR evidence synthesis of socio-technical resilience and responsible technology adoption
    Byron Nelson Zurita Lara · 2026 · Social Sciences & Humanities Open