Finetuning Large Language Models for Vulnerability Detection

This paper presents the results of finetuning large language models (LLMs) for the task of detecting vulnerabilities in Java source code. We leverage WizardCoder, a recent improvement of the state-of-the-art LLM StarCoder, and adapt it for vulnerability detection through further finetuning. To accelerate training, we modify WizardCoder’s training procedure, also we investigate optimal training regimes. For the imbalanced dataset with many more negative examples than positive, we also explore different techniques to improve classification performance. The finetuned WizardCoder model achieves improvement in ROC AUC and F1 measures on balanced and imbalanced vulnerability datasets over CodeBERT-like model,…

• MO
  Ministry of Education and Science of the Republic of Kazakhstan

  Award: BR21882268