This light-powered AI can spot deepfakes with nearly 98% accuracy

AI Summary

UCLA researchers developed a light-powered AI system that detects deepfakes with nearly 98% accuracy while analyzing multiple videos simultaneously. Its speed, low energy use, and reported resistance to attacks could make it useful for screening AI-generated video.

UCLA researchers built an AI system that uses light to analyze more than a dozen videos simultaneously, detecting deepfakes with nearly 98% accuracy. Its speed, low energy demands, and resistance to attacks could make it a powerful tool for screening the growing flood of AI-generated video.