DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models

arXiv:2402.13291v1 Announce Type: new
Abstract: The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven difficult. A promising direction to solve this challenge is by leveraging large language models (LLMs), which are increasingly used to solve various programming tasks. In this paper, we investigate the effectiveness of LLMs for solving code-repair task. We show that the task …

arxiv automated bugs challenge cs.cr cs.lg cs.pl cs.se fix interest language language models large program repair research security semantic system vulnerabilities