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

What happened

This light-powered AI can spot deepfakes with nearly 98% accuracy, according to ScienceDaily. UCLA researchers built an AI system that operates with 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.

Science News from research organizations This light-powered AI can spot deepfakes with nearly 98% accuracy Date: October 1, 2026 Source: Light Publishing Center, Changchun Institute of Optics, Fine Mechanics And Physics, CAS Summary: UCLA researchers built an AI system that operates with light to analyze more than a dozen videos simultaneously, detecting deepfakes with nearly 98% accuracy. Share: Facebook Twitter Pinterest LinkedIN Email FULL STORY Researchers at the University of California, Los Angeles (UCLA) have created a new optical-neural processor that operates with light to help identify deepfake videos quickly and accurately.

Unlike conventional systems that typically examine videos one after another using digital hardware, the UCLA technology can analyze 15 or more video streams at the same time. Many advanced deepfake detectors depend on enormous amounts of digital computation.