mlsanityData to 7 Oct 2026

When LLMs Meet Cybersecurity: A Systematic Literature Review

arXiv 2405.03644 ↗First posted 6 May 2024cs.CR cs.AIcited by 70

Not on the map. Why?

Abstract (arXiv)

The rapid development of large language models (LLMs) has opened new avenues across various fields, including cybersecurity, which faces an evolving threat landscape and demand for innovative technologies. Despite initial explorations into the application of LLMs in cybersecurity, there is a lack of a comprehensive overview of this research area. This paper addresses this gap by providing a systematic literature review, covering the analysis of over 300 works, encompassing 25 LLMs and more than 10 downstream scenarios. Our comprehensive overview addresses three key research questions: the construction of cybersecurity-oriented LLMs, the application of LLMs to various cybersecurity tasks, the challenges and further research in this area. This study aims to shed light on the extensive potential of LLMs in enhancing cybersecurity practices and serve as a valuable resource for applying LLMs in this field. We also maintain and regularly update a list of practical guides on LLMs for cybersecurity at https://github.com/tmylla/Awesome-LLM4Cybersecurity.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 230 of its 359 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

230 of 359 references.

References · 230

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  11. 2022Emergent Abilities of Large Language Modelscited by 2,483
  12. 2020Extracting Training Data from Large Language Modelscited by 2,144
38 more
  1. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  2. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2024Mixtral of Expertscited by 1,785
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  7. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  8. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  9. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  10. 2023Teaching Large Language Models to Self-Debugcited by 963
  11. 2022Toy Models of Superpositioncited by 928
  12. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  13. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  14. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  15. 2021GPT Understands, Toocited by 715
  16. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  17. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  18. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  19. 2023The Falcon Series of Open Language Modelscited by 526
  20. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 520
  21. 2024Large Language Models: A Surveycited by 506
  22. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  23. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  24. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  25. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
  26. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agentscited by 476
  27. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 457
  28. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  29. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 417
  30. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  31. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  32. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  33. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  34. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  35. 2020A Survey on Neural Network Interpretabilitycited by 291
  36. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  37. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  38. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easilycited by 242

50 most cited of 230 All 230 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 42; 2026: 22.

70 papers.

Sort:

By area:

  1. 2025SAGA: A Security Architecture for Governing AI Agentic Systemscited by 45
  2. 2025Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Reportcited by 28
  3. 2025Frontier AI's Impact on the Cybersecurity Landscapecited by 21
  4. 2025Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Reportcited by 21
  5. 2025ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigationcited by 15
  6. 2025CORTEX: Collaborative LLM Agents for High-Stakes Alert Triagecited by 14
  7. 2025CyberRAG: An Agentic RAG cyber attack classification and reporting toolcited by 11
  8. 2025Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agentscited by 11
  9. 2026Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenderscited by 10
  10. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  11. 2024Integrating Large Language Models with Internet of Things Applicationscited by 7
  12. 2026Digital Red Queen: Adversarial Program Evolution in Core War with LLMscited by 7
38 more
  1. 2026Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Reportcited by 7
  2. 2026Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agentscited by 6
  3. 2025eX-NIDS: A Framework for Explainable Network Intrusion Detection Leveraging Large Language Modelscited by 5
  4. 2024Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reductioncited by 4
  5. 2025ARACNE: An LLM-Based Autonomous Shell Pentesting Agentcited by 4
  6. 2025DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environmentscited by 4
  7. 2025ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphscited by 4
  8. 2025Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Huntingcited by 4
  9. 2025From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localizationcited by 4
  10. 2024Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Frameworkcited by 3
  11. 2025OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Promptingcited by 3
  12. 2025ARCeR: an Agentic RAG for the Automated Definition of Cyber Rangescited by 3
  13. 2025Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applicationscited by 3
  14. 2025Evaluating Language Models For Threat Detection in IoT Security Logscited by 3
  15. 2025Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensicscited by 3
  16. 2025OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Modelscited by 3
  17. 2025Toward Cybersecurity-Expert Small Language Modelscited by 3
  18. 2025Gen-Review: A Large-scale Dataset of AI-Generated (and Human-written) Peer Reviewscited by 3
  19. 2024The Best Defense is a Good Offense: Countering LLM-Powered Cyberattackscited by 2
  20. 2025Can LLMs effectively provide game-theoretic-based scenarios for cybersecurity?cited by 2
  21. 2025Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessmentcited by 2
  22. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  23. 2025SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypotscited by 2
  24. 2025Ranking-Enhanced Anomaly Detection Using Active Learning-Assisted Attention Adversarial Dual AutoEncoderscited by 2
  25. 2025The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelinescited by 2
  26. 2026Autonomous LLM Agents & CTFs: A Second Lookcited by 2
  27. 2025Large Language Models powered Malicious Traffic Detection: Architecture, Opportunities and Case Studycited by 1
  28. 2025Can LLMs Assist Computer Education? an Empirical Case Study of DeepSeekcited by 1
  29. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 1
  30. 2025A Survey: Towards Privacy and Security in Mobile Large Language Modelscited by 1
  31. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  32. 2026Automated Post-Incident Policy Gap Analysis via Threat-Informed Evidence Mapping using Large Language Modelscited by 1
  33. 2026Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregationcited by 1
  34. 2026Supporting Artifact Evaluation with LLMs: A Study with Published Security Research Paperscited by 1
  35. 2026Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Modelscited by 1
  36. 2026Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Frameworkcited by 1
  37. 2026Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggerscited by 1
  38. 2026Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysiscited by 1

50 most cited of 70 All 70 (JSON)