DarkPatternLLM is a project aimed at detecting and combating dark patterns on websites using advanced Language Models (LLMs). This tool provides users with a more transparent and user-friendly online experience.
The project leverages three state-of-the-art language models: RoBERTa, XLNet, and BERT to detect and highlight potential dark patterns on websites.
A comprehensive dataset has been gathered from various sources to train and fine-tune the models for accurate pattern detection.
Receive real-time alerts when visiting a website that employs deceptive design practices.
Access resources within the extension to learn more about dark patterns and how to protect yourself online.
To install the DarkPatternLLM, follow these steps:
- Download the extension from the Chrome Web Store.
- Open Google Chrome and navigate to the "Extensions" page (
chrome://extensions/). - Drag and drop the downloaded extension file onto the extensions page to install it.
After installation, the DarkPatternLLM icon will appear in your browser toolbar. Simply visit any website, and the extension will automatically analyze the page for dark patterns. If a dark pattern is detected, you will receive a notification, and the relevant elements will be highlighted on the page.
We welcome contributions! If you want to contribute to the project, please follow these steps:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Make your changes and submit a pull request.