Curated systematic literature review of 756+ papers on LLM applications in cybersecurity, covering threat intelligence, vulnerability detection, fuzzing, attack/defense, and future research directions.
π RQ1: Domain LLMs | π― RQ2: Applications | π€ RQ3: Future Directions
π[2026-06-15] We have updated the related papers up to 2026/06/15, with 108 new papers added.
π[2026-02-09] We have updated the related papers up to 2026/01/31, with 80 new papers added (2025.08.31-2026.01.31).
π[2025-11-17] We have updated the related papers up to 2025/08/31, with 176 new papers added (2025.03.01-2025.08.31).
π[2025-03-03] We have updated the related papers up to 2025/02/28, with 33 new papers added (2025.01.01-2025.02.28).
π[2025-01-21] We have updated the related papers up to 2024/12/31, with 74 new papers added (2024.09.01-2024.12.31).
π[2025-01-08] We have included the publication venues for each paper.
π[2024-09-21] We have updated the related papers up to 2024/08/31, with 75 new papers added (2024.06.01-2024.08.31).
| RQ | Category | Papers | Percentage | Trend |
|---|---|---|---|---|
| RQ1 | π Evaluation Benchmarks | 67 | 8.9% | π Stable |
| π§ Fine-tuned LLMs | 36 | 4.8% | π Stable | |
| RQ2 | π‘οΈ LLM Assisted Defense | 130 | 17.2% | π Growing |
| π Vulnerability Detection | 106 | 14.0% | π Growing | |
| βοΈ LLM Assisted Attack | 110 | 14.6% | π₯ Hot | |
| π¨ Program/Vulnerability Repair | 72 | 9.5% | π Stable | |
| π¦ Others | 61 | 8.1% | π Stable | |
| π― Threat Intelligence | 53 | 7.0% | π Stable | |
| π FUZZ | 26 | 3.4% | π Stable | |
| β οΈ Insecure Code Generation | 32 | 4.2% | π« Unmaintained | |
| RQ3 | π€ Agent4Cybersecurity | 63 | 8.3% | π Emerging |
π View Full Literature Review β
The complete literature review with 756+ papers has been moved to a separate file for better readability.
RQ2: LLM Applications in Cybersecurity
RQ3: Future Research Directions
@article{zhang2025llms,
title={When llms meet cybersecurity: A systematic literature review},
author={Zhang, Jie and Bu, Haoyu and Wen, Hui and Liu, Yongji and Fei, Haiqiang and Xi, Rongrong and Li, Lun and Yang, Yun and Zhu, Hongsong and Meng, Dan},
journal={Cybersecurity},
volume={8},
number={1},
pages={1--41},
year={2025},
publisher={SpringerOpen}
}