Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mnns/LLMFuzzer
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥
https://github.com/mnns/LLMFuzzer
ai cybersecurity llm llmsecurity
Last synced: 4 months ago
JSON representation
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥
- Host: GitHub
- URL: https://github.com/mnns/LLMFuzzer
- Owner: mnns
- License: mit
- Created: 2023-05-20T16:40:00.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-02-12T07:22:56.000Z (about 1 year ago)
- Last Synced: 2024-08-02T15:11:53.089Z (7 months ago)
- Topics: ai, cybersecurity, llm, llmsecurity
- Language: Python
- Homepage:
- Size: 50.8 KB
- Stars: 201
- Watchers: 4
- Forks: 27
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-gpt-security - LLMFuzzer - LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. (Tools / Detecting)
- awesome-llm-security - LLMFuzzer
- Awesome-LLM4Security - LLMFuzzer
- Awesome-LLM4Security - LLMFuzzer
README
# 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠
[](https://forthebadge.com)
[](https://forthebadge.com)
[](https://forthebadge.com)
----------------------------------------------------------------
## Project Status: Unmaintained
This project is no longer actively maintained. You are welcome to fork and continue its development on your own. Thank you for your interest and support.
----------------------------------------------------------------
LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥
## 🎯 Who is this for?
If you're a security enthusiast, a pentester, or a cybersec researcher who loves to find and exploit vulnerabilities in AI systems, LLMFuzzer is the perfect tool for you. It's built to make your testing process streamlined and efficient. 🕵️♀️
## 🌟 Features
- Robust fuzzing for LLMs 🧪
- LLM API integration testing 🛠️
- Wide range of fuzzing strategies 🌀
- Modular architecture for easy extendability 📚
## 🔥 Roadmap
* Adding more attacks
* HTML Report as output
* Multiple Connectors (JSON-POST, RAW-POST, QUERY-GET)
* Multiple Comparers
* Proxy Support
* Dual-LLM (Side LLM observation)
* Autonomous Attack Mode
## 🚀 Get Started
1. Clone the repo
```bash
git clone https://github.com/mnns/LLMFuzzer.git
```
2. Navigate to the project directory
```bash
cd LLMFuzzer
```
3. Install dependencies
```bash
pip install -r requirements.txt
```
4. Edit **llmfuzzer.cfg** with your LLM API endpoint (LLMFuzzer -> Your Application -> LLM)
```bash
Connection:
Type: HTTP-API
Url: "http://localhost:3000/chat" # Your LLM API
Content: JSON
Query-Attribute: "query" # Your JSON query attribute
Output-Attribute: "answer" # Your JSON response attribute
Headers: {'enwiki_session': '17ab96bd8ffbe8ca58a78657a918558'} # Add HTTP Headers if needed
Cookie: {'enwiki_session': '17ab96bd8ffbe8ca58a78657a918558'} # Add Cookies if needed
```
5. Run LLMFuzzer
```bash
python main.py
```
## 📚 Documentation
We are working on full documentation. It will cover detailed information about the architecture, different fuzzing strategies, examples, and how to extend the tool.
## 🤝 Contributing
We welcome all contributors who are passionate about improving LLMFuzzer. See our contributing guidelines for ways to get started. 🤗
## 💼 License
LLMFuzzer is licensed under the MIT License. See the LICENSE file for more details.
## 🎩 Acknowledgments
LLMFuzzer couldn't exist without the community. We appreciate all our contributors and supporters. Let's make AI safer together! 💖