garak checks if an LLM can be made to fail in a way we don’t want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you know nmap or msf / Metasploit Framework, garak does somewhat similar things to them, but for LLMs.
garak focuses on ways of making an LLM or dialog system fail. It combines static, dynamic, and adaptive probes to explore this.
garak‘s a free tool. We love developing it and are always interested in adding functionality to support applications.
currently supports:
garak is a command-line tool. It’s developed in Linux and OSX.
pipJust grab it from PyPI and you should be good to go:
python -m pip install -U garakpipThe standard pip version of garak is updated periodically. To get a fresher version from GitHub, try:
python -m pip install -U git+https://github.com/NVIDIA/garak.git@mainFor more information click here.
This cheat sheet covers the essential Kali Linux commands every pentester and ethical hacker uses…
When I first started learning malware analysis and reverse engineering, I thought the hardest part…
Both git fetch and git pull talk to a remote repository, but they do very different things to your…
Sometimes the change you need already exists, just on the wrong branch. A hotfix lands…
Email is still one of the most important communication channels inside modern applications. Password resets,…
Nginx is a high-performance web server and reverse proxy trusted by some of the largest…