Instruction Tuning for Secure Code Generation

TL;DR

This paper introduces SafeCoder, a method for instruction tuning language models to generate more secure code without sacrificing utility, addressing a critical security gap in existing models.

Contribution

SafeCoder is a security-centric fine-tuning approach that combines security and utility optimization, significantly improving code safety in language models.

Findings

Security improved by about 30%

Effective across various LMs and datasets

Maintains utility while enhancing security

Abstract

Modern language models (LMs) have gained widespread acceptance in everyday and professional contexts, particularly in programming. An essential procedure enabling this adoption is instruction tuning, which substantially enhances LMs' practical utility by training them to follow user instructions and human preferences. However, existing instruction tuning schemes overlook a crucial aspect: the security of generated code. As a result, even the state-of-the-art instruction-tuned LMs frequently produce unsafe code, posing significant security risks. In this work, we introduce SafeCoder to address this gap. SafeCoder performs security-centric fine-tuning using a diverse and high-quality dataset that we collected using an automated pipeline. We integrate the security fine-tuning with standard instruction tuning, to facilitate a joint optimization of both security and utility. Despite its simplicity, we show that SafeCoder is effective across a variety of popular LMs and datasets. It is able to drastically improve security (by about 30%), while preserving utility.