Deep learning methods for deepfakes detection

Monash University, Australia

Updated: 2 days ago
Location: Melbourne, VICTORIA

Deepfakes, derived from "deep learning" and "fake," involve techniques that merge the face images of a target person with a video of a different source person. This process creates videos where the target person appears to be performing actions or speaking as the source person. In a broader context, deepfakes encompass other categories such as lip-sync and puppet-master. Lip-sync deepfakes alter videos to synchronize mouth movements with a provided audio track. Puppet-master deepfakes depict a target person (the puppet) whose facial expressions, eye movements, and head gestures mimic those of another person (the master) recorded on camera. This project focuses on exploring deep learning methodologies specifically designed for detecting and mitigating the presence of deepfakes in digital content.


Required knowledge
  • Python programming
  • Machine learning background
  • Image analysis
  • Video analysis
  • Audio analysis

Similar Positions