Open-Source Toolkit

logo

Deepstar is a new open source toolkit developed by ZeroFox.

Deepstar is based on research into deepfake videos and the difficulty in quickly developing and enhancing detection capabilities. The toolkit was designed to help ZeroFox and others in the community build, test, and enhance techniques for detecting deepfakes.

The Deepstar toolkit and library will help defenders get ahead of this problem. We encourage the larger community to create and add new plug-ins and contribute to the video library so that the community can continue to elevate the state of our defenses for deepfake detection.

Interested in exploring the toolkit yourself? You can access Deepstar on GitHub.

Black Hat 2019: Playing Offense and Defense with Deepfakes

Deepstar Includes

  1. 01
    Code for aiding in the creation of deepfake datasets, testing, and enhancement of detection algorithms.
  2. 02
    A curated library of deepfake and real videos from YouTube – these help in training AI models.
  3. 03
    A plug-in framework, enabling researchers to easily test or re-train and compare the performance of different classifiers.

Contribute to Deepstar

Access Deepstar on GitHub

Enhance Deepstar detection models

Add deepfake samples to url library

Build deepfake plugins

See ZeroFox in action