Translate to multiple languages

Subscribe to my Email updates
Enjoy what you've read, make sure you subscribe to my Email Updates

Friday, June 01, 2018

Researchers create photo filter that disables facial recognition | Planet Biometrics

Photo: Parham Aarabi
"Professor Parham Aarabi and graduate student Avishek Bose are using "neural net based constrained optimization" to disrupt face detection software" reports Planet Biometrics.

Photo: Planet Biometrics

The University of Toronto researchers used existing knowledge of detection software that says "small, often imperceptible, perturbations can be added to images to fool a typical classification network into misclassifying them." Their dynamic "attack" algorithm "produc[es] small perturbations that, when added to an input face image, causes the pre-trained face detector to fail."

Aarabi and Bose designed two different, opposing neural networks — one that attempts to identify faces and the other that works to "disrupt" that identification — using 'adversarial training', a deep learning technique that puts two opposing AI algorithms in a sort of digital cage match.

Source: Planet Biometrics