Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.06645 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915538893012992 |
|---|---|
| author | Wei, Zhiyuan Yang, Xiaoxuan Sun, Jing Zhang, Zijian |
| author_facet | Wei, Zhiyuan Yang, Xiaoxuan Sun, Jing Zhang, Zijian |
| contents | The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for software security. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing, their potential for automated code vulnerability detection remains underexplored. This paper presents FineSec, a novel framework that harnesses LLMs through knowledge distillation to enable efficient and precise vulnerability identification in C/C++ codebases. FineSec utilizes knowledge distillation to transfer expertise from large teacher models to compact student models, achieving high accuracy with minimal computational cost. By integrating data preparation, training, evaluation, and continuous learning into a unified, single-task workflow, FineSec offers a streamlined approach. Extensive evaluations on C/C++ codebases demonstrate its superiority over both base models and larger LLMs in identifying complex vulnerabilities and logical flaws, establishing FineSec as a practical and scalable solution for real-world software security. To facilitate reproducibility, the datasets, source code, and experimental results are made publicly available at: https://github.com/yangxiaoxuan123/FineSec_detect. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06645 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distilling Lightweight Language Models for C/C++ Vulnerabilities Wei, Zhiyuan Yang, Xiaoxuan Sun, Jing Zhang, Zijian Cryptography and Security Artificial Intelligence The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for software security. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing, their potential for automated code vulnerability detection remains underexplored. This paper presents FineSec, a novel framework that harnesses LLMs through knowledge distillation to enable efficient and precise vulnerability identification in C/C++ codebases. FineSec utilizes knowledge distillation to transfer expertise from large teacher models to compact student models, achieving high accuracy with minimal computational cost. By integrating data preparation, training, evaluation, and continuous learning into a unified, single-task workflow, FineSec offers a streamlined approach. Extensive evaluations on C/C++ codebases demonstrate its superiority over both base models and larger LLMs in identifying complex vulnerabilities and logical flaws, establishing FineSec as a practical and scalable solution for real-world software security. To facilitate reproducibility, the datasets, source code, and experimental results are made publicly available at: https://github.com/yangxiaoxuan123/FineSec_detect. |
| title | Distilling Lightweight Language Models for C/C++ Vulnerabilities |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2510.06645 |