Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model

TL;DR

SecCoderX is an online reinforcement learning framework that enhances large language models to generate secure, functional code by leveraging vulnerability detection and a specialized reward model, significantly improving security without utility loss.

Contribution

The paper introduces SecCoderX, a novel online RL approach that aligns code generation with security and functionality, overcoming the security-utility trade-off in prior methods.

Findings

Achieves approximately 10% higher Effective Safety Rate (ESR) than unaligned models.

Outperforms prior methods that degrade ESR by 14-54%.

Provides publicly available code, dataset, and model checkpoints.

Abstract

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.