A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair
This work addresses the problem of automated vulnerability repair for software security, but it is incremental as it benchmarks existing models on new data without introducing a novel method.
The study evaluated pre-trained language models CodeBERT and CodeT5 for automated vulnerability patching across multiple datasets and languages, finding that CodeBERT performs better in fragmented contexts while CodeT5 excels in capturing complex patterns and scalability, but both models struggle to generalize to unseen vulnerabilities.
Software vulnerabilities pose significant security threats, requiring effective mitigation. While Automated Program Repair (APR) has advanced in fixing general bugs, vulnerability patching, a security-critical aspect of APR remains underexplored. This study investigates pre-trained language models, CodeBERT and CodeT5, for automated vulnerability patching across six datasets and four languages. We evaluate their accuracy and generalization to unknown vulnerabilities. Results show that while both models face challenges with fragmented or sparse context, CodeBERT performs comparatively better in such scenarios, whereas CodeT5 excels in capturing complex vulnerability patterns. CodeT5 also demonstrates superior scalability. Furthermore, we test fine-tuned models on both in-distribution (trained) and out-of-distribution (unseen) datasets. While fine-tuning improves in-distribution performance, models struggle to generalize to unseen data, highlighting challenges in robust vulnerability detection. This study benchmarks model performance, identifies limitations in generalization, and provides actionable insights to advance automated vulnerability patching for real-world security applications.