BrokenHill

by BishopFox · Agent Tool · ★ 158

About BrokenHill

Broken Hill Broken Hill is a productionized, ready-to-use automated attack tool that generates crafted prompts to bypass restrictions in large language models (LLMs) using the greedy coordinate gradient (GCG) attack described in the "Universal and Transferable Adversarial Attacks on Aligned Language Models" paper by Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, and Matt Fredrikson. Broken Hill can generate robust prompts that successfully jailbreak LLMs configured differently than the one used to generate the prompts.

Quick Facts

Stars158
Forks24
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score53.7203173499824/100
Open Issues2
Last Updated2024-12-18
Created2024-07-25
Platformspython
Est. Tokens~325k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is BrokenHill?

BrokenHill is A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs). It is categorized as a Agent Tool with 158 GitHub stars.

What programming language is BrokenHill written in?

BrokenHill is primarily written in Python.

How do I install or use BrokenHill?

You can find installation instructions and usage details in the BrokenHill GitHub repository at github.com/BishopFox/BrokenHill. The project has 158 stars and 24 forks, indicating an active community.

What license does BrokenHill use?

BrokenHill is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools