Learning to Repair Software Vulnerabilities with Generative Adversarial Networks

TL;DR

This paper introduces an adversarial learning method using GANs for automated software vulnerability repair, achieving competitive results without needing paired training data, and applicable to other code-related tasks.

Contribution

The paper presents a novel GAN-based approach for software vulnerability repair that does not require paired data and is adaptable to various code correction tasks.

Findings

Effective in repairing vulnerabilities close to seq2seq methods

Does not require paired labeled examples

Applicable to other code-related problems

Abstract

Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial learning approach is an effective technique for repairing software vulnerabilities, performing close to seq2seq approaches that require labeled pairs. The proposed Generative Adversarial Network approach is application-agnostic in that it can be applied to other problems similar to code repair, such as grammar correction or sentiment translation.