Carnegie Mellon University
January 17, 2018

Bauer's research on facial recognition technology cited in Digital Trends

Lujo Bauer and his research team recently developed eyeglasses that are capable of fooling facial recognition algorithms. In his recent study, titled “Adversarial Generative Nets: Neural Network Attacks on State-of-the-Art Face Recognition,” Bauer and his team explain how they developed five pairs of glasses that 90% of the population could successfully wear to bypass surveillance systems. After concluding their study, Bauer and his team notified the Transportation Security Administration (TSA)—an organization that already uses facial recognition technology—of their findings, and recommended that they require subjects to remove things like hats and glasses before conducting facial recognition scans. Read the article.