An Empirical Study of Automated Vulnerability Localization with Large Language Models

arXiv:2404.00287v1 Announce Type: cross
Abstract: Recently, Automated Vulnerability Localization (AVL) has attracted much attention, aiming to facilitate diagnosis by pinpointing the lines of code responsible for discovered vulnerabilities. Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in vulnerability localization remains underexplored. In this work, we perform the first comprehensive study of LLMs for AVL. Our investigation encompasses 10+ leading LLMs suitable for code analysis, including ChatGPT and various open-source models, across three architectural types: encoder-only, …

arxiv attention automated code cs.cr cs.se diagnosis domains language language models large llms localization responsible study vulnerabilities vulnerability work