Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915784080490496 |
|---|---|
| author | Wu, Tianyi Du, Mingzhe Liu, Yue Yang, Chengran Zhuo, Terry Yue Zhang, Jiaheng Ng, See-Kiong |
| author_facet | Wu, Tianyi Du, Mingzhe Liu, Yue Yang, Chengran Zhuo, Terry Yue Zhang, Jiaheng Ng, See-Kiong |
| contents | Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing secure code alignment methods often suffer from a functionality--security paradox, improving security at the cost of substantial utility degradation. We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation. SecCoderX first bridges vulnerability detection and secure code generation by repurposing mature detection resources in two ways: (i) synthesizing diverse, reality-grounded vulnerability-inducing coding tasks for online RL rollouts, and (ii) training a reasoning-based vulnerability reward model that provides scalable and reliable security supervision. Together, these components are unified in an online RL loop to align code LLMs to generate secure and functional code. Extensive experiments demonstrate that SecCoderX achieves state-of-the-art performance, improving Effective Safety Rate (ESR) by approximately 10% over unaligned models, whereas prior methods often degrade ESR by 14-54%. We release our code, dataset and model checkpoints at https://github.com/AndrewWTY/SecCoderX. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07422 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model Wu, Tianyi Du, Mingzhe Liu, Yue Yang, Chengran Zhuo, Terry Yue Zhang, Jiaheng Ng, See-Kiong Cryptography and Security Artificial Intelligence Computation and Language Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing secure code alignment methods often suffer from a functionality--security paradox, improving security at the cost of substantial utility degradation. We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation. SecCoderX first bridges vulnerability detection and secure code generation by repurposing mature detection resources in two ways: (i) synthesizing diverse, reality-grounded vulnerability-inducing coding tasks for online RL rollouts, and (ii) training a reasoning-based vulnerability reward model that provides scalable and reliable security supervision. Together, these components are unified in an online RL loop to align code LLMs to generate secure and functional code. Extensive experiments demonstrate that SecCoderX achieves state-of-the-art performance, improving Effective Safety Rate (ESR) by approximately 10% over unaligned models, whereas prior methods often degrade ESR by 14-54%. We release our code, dataset and model checkpoints at https://github.com/AndrewWTY/SecCoderX. |
| title | Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2602.07422 |