PROJECT TITLE :

Movee: Video Liveness Verification for Mobile Devices Using Built-In Motion Sensors

ABSTRACT:

The ubiquitous and connected nature of camera-equipped mobile devices has greatly increased the worth and importance of visual info they capture. Today, broadcasting videos from camera phones uploaded by unknown users is admissible on news networks, and banking customers expect to be in a position to deposit checks using mobile devices. During this paper, we introduce Movee, a system that addresses the basic question of whether or not the visual stream uploaded by a user has been captured carry on a mobile device, and has not been tampered with by an adversary. Movee leverages the mobile device motion sensors and therefore the intrinsic user movements throughout the shooting of the video. Movee exploits the observation that the movement of the scene recorded on the video stream should be related to the movement of the device simultaneously captured by the accelerometer. Contrary to existing algorithms, Movee has the distinctive strength of not depending on the audio track. We tend to introduce novel attacks that target Movee's defenses, to fabricate acceleration information that mimics the motion observed in targeted videos. We have a tendency to use smartphones and wearable smart glasses to gather both real and attack information from 13 users. Our experiments show that Movee is in a position to efficiently detect human and automatically generated plagiarized videos: Movee's accuracy ranges between sixty eight-ninety three percent on a smartphone, and between seventy six-ninety one % on a Google Glass device.