amazon-science/TurboFuzzLLM

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

35
/ 100
Emerging

This tool helps AI safety researchers and red teamers automatically find weaknesses in Large Language Models (LLMs). It takes a list of potentially harmful questions and, through an iterative process, generates new, subtly modified prompts that can 'jailbreak' the LLM. The output is a collection of effective adversarial prompt templates that show how the model can be tricked into generating undesirable responses, allowing for improved AI safeguards.

Use this if you are responsible for evaluating and improving the safety of LLMs by systematically identifying their vulnerabilities to adversarial prompts.

Not ideal if you are looking for a general-purpose prompt engineering tool or a way to train a base LLM from scratch.

AI safety LLM red teaming vulnerability testing adversarial prompt generation model security
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

22

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Nov 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/amazon-science/TurboFuzzLLM"

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