
Existing large language models and deep learning-based automated program repair techniques can fix only a small number of real-world Java security vulnerabilities, with Codex exhibiting the best fixing capability among the models studied. Fine-tuning language models with general program repair data can improve their vulnerability fixing abilities, but they still struggle to fix many complex vulnerability types.


coremsg

evaluating-the-effectiveness-of-neural-networks-in-fixing-real-world-java-security-vulnerabilities


Evaluating the Effectiveness of Neural Networks in Fixing Real-World Java Security Vulnerabilities


title_rewrite


Fine-tuned Large Language Models, particularly Mistral, show promise in automating code vulnerability repair, outperforming existing methods even with stricter evaluation metrics and highlighting the importance of dataset integrity in accurately assessing model performance.


improving-automated-code-vulnerability-repair-with-large-language-models-a-comparative-study


Improving Automated Code Vulnerability Repair with Large Language Models: A Comparative Study
