Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.23674 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912672876855296 |
|---|---|
| author | Wang, Bin Li, Hui Liu, AoFan Yang, BoTao Yang, Ao Zhong, YiLu Huang, Weixiang Zhang, Yanping Huang, Runhuai Zeng, Weimin |
| author_facet | Wang, Bin Li, Hui Liu, AoFan Yang, BoTao Yang, Ao Zhong, YiLu Huang, Weixiang Zhang, Yanping Huang, Runhuai Zeng, Weimin |
| contents | Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhances code security by integrating Retrieval-Augmented Generation (RAG) techniques with guided self-reflection mechanisms inherent in LLMs. Unlike traditional approaches that rely on fine-tuning LLMs or developing specialized secure code datasets - processes that can be resource-intensive - RefleXGen iteratively optimizes the code generation process through self-assessment and reflection without the need for extensive resources. Within this framework, the model continuously accumulates and refines its knowledge base, thereby progressively improving the security of the generated code. Experimental results demonstrate that RefleXGen substantially enhances code security across multiple models, achieving a 13.6% improvement with GPT-3.5 Turbo, a 6.7% improvement with GPT-4o, a 4.5% improvement with CodeQwen, and a 5.8% improvement with Gemini. Our findings highlight that improving the quality of model self-reflection constitutes an effective and practical strategy for strengthening the security of AI-generated code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23674 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RefleXGen:The unexamined code is not worth using Wang, Bin Li, Hui Liu, AoFan Yang, BoTao Yang, Ao Zhong, YiLu Huang, Weixiang Zhang, Yanping Huang, Runhuai Zeng, Weimin Software Engineering Artificial Intelligence Cryptography and Security Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhances code security by integrating Retrieval-Augmented Generation (RAG) techniques with guided self-reflection mechanisms inherent in LLMs. Unlike traditional approaches that rely on fine-tuning LLMs or developing specialized secure code datasets - processes that can be resource-intensive - RefleXGen iteratively optimizes the code generation process through self-assessment and reflection without the need for extensive resources. Within this framework, the model continuously accumulates and refines its knowledge base, thereby progressively improving the security of the generated code. Experimental results demonstrate that RefleXGen substantially enhances code security across multiple models, achieving a 13.6% improvement with GPT-3.5 Turbo, a 6.7% improvement with GPT-4o, a 4.5% improvement with CodeQwen, and a 5.8% improvement with Gemini. Our findings highlight that improving the quality of model self-reflection constitutes an effective and practical strategy for strengthening the security of AI-generated code. |
| title | RefleXGen:The unexamined code is not worth using |
| topic | Software Engineering Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2510.23674 |