Using your phone in a public place for texting or entering private information can always be a bit unnerving because you never know who may be looking over your shoulder. Thanks to two Google researchers and machine learning, that fear may become a thing of the past.
See Jung Ryu and Florian Schroff created an algorithm using existing facial recognition technology that detects individuals lurking behind you within two milliseconds. Within 47 milliseconds, the AI can discern a face. The pair plan to show off the technology next week at the Neural Information Processing Systems Conference in Long Beach, California, and have released an accompanying demo video.
A brief description of the panel discussion - entitled Electronic Screen Protector with Efficient and Robust Mobile Vision - explains the tech:
Face authentication, in the context of privacy for phones, has been explored for some time. However, face recognition alone is not enough when you want to have private online conversations or watch a confidential video in a crowded space where there are many other people present. Each of them may or may not be looking at your private content displayed on your device, e.g. a smart phone. Because of the quick, robust, and accurate gaze detection mobile model we can now easily identify the face identity and gaze simultaneously in real time. Hence, the application, an electronic screen protector, can enable its enrolled users to continue reading private and confidential contents on your mobile device, while protecting their privacy from onlookers in a crowded space such as the subway or an elevator.
According to ZDNet, the technology includes a facial-recognition neural network called FaceNet, created in 2015 by Schroff and others. It also uses a gaze-estimation neural network called GazeNet.
While the technology seems to be further along that an early development stage, there is no indication when, or if, Google plans on implementing the "electronic screen protector" in its Pixel device anytime soon, or licensing it out to other vendors.
Source and image: ZDNet