pdparchitect/llm-hacking-database

This repository contains various attack against Large Language Models.

29
/ 100
Experimental

This database helps security researchers and penetration testers understand and replicate attacks against large language models (LLMs). It takes descriptions of various 'jailbreaking' techniques as input and provides concrete examples of how to execute them, revealing vulnerabilities in LLM-powered applications. Security analysts and red teamers who are responsible for evaluating the safety of AI systems would use this.

132 stars. No commits in the last 6 months.

Use this if you need to identify and demonstrate security flaws or unintended behaviors in AI chatbots and LLMs.

Not ideal if you are looking for defensive programming strategies or code to directly implement LLM security patches.

AI Security Penetration Testing Red Teaming Vulnerability Research LLM Testing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

132

Forks

11

Language

License

Last pushed

May 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/pdparchitect/llm-hacking-database"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.