---
title: "PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing | Papers With Code Cyber"
description: "Trending AI research papers with code, datasets, methods, and evaluation leaderboards."
canonical: "https://paperswithcode-cyber.com/paper/56"
type: "paper"
---

# PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing

External resource · 56

## Tasks

- [Exploit construction and validation](https://paperswithcode-cyber.com/tasks/cyberintel-exploit-development)
- [Penetration testing](https://paperswithcode-cyber.com/tasks/cyberintel-penetration-testing)

## Code repositories

- [GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT)

## Paper resources

- [Source](https://www.usenix.org/conference/usenixsecurity24/presentation/deng)