---
id: 8570
title: "Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models"
source_domain: projectzero.google
source_url: "https://projectzero.google/2024/06/project-naptime.html"
published_at: "2024-06-20T00:00:00Z"
tags: ["ai-security", "offensive-security", "llm", "research", "vulnerability-discovery", "project-naptime"]
phying_url: "https://phying.com/item/8570"
lang: en
---

# Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models

## Summary

Project Naptime evaluates the offensive security capabilities of large language models, presenting a methodology, tooling setup, and early successes finding real vulnerabilities.

## Intelligence Metadata

- **Sources:** projectzero.google
- **Published:** 2024-06-20T00:00:00Z
- **Original:** https://projectzero.google/2024/06/project-naptime.html
- **Phying News:** https://phying.com/item/8570