How I Built the World's Most Powerful Deepfake Detector for €100
summary
Mathis Hammel explains a method to detect images produced by ThisPersonDoesNotExist.com with claimed 100% accuracy and a way to determine the exact time a generated face was created. The talk covers basic machine-learning concepts behind GANs and also describes a technique to generate nearly undetectable fake faces; no prerequisites are required.
AI-written summary · about
chapters (4)
related talks
46mHow I built the world’s most efficient deepfake detector with $100
47mHow I designed the most efficient deepfake detector in the world with $100
27mTruth or Fiction The Art of Unveiling DeepFakes in Text, Audio, Image
01h 04mPushing Deepfakes to The Limit - Fake Video Calls With AI
30mAI-Generated Synthetic Media, aka Deepfakes and its impact
58mPushing Deepfakes to the Limit-Fake video calls with AI
38mDIY Deep Fakes
27mAl-Generated Attacks: The New Era of Threats to Authentication