The ubiquitous and connected nature of cameraequipped mobile devices has greatly increased the value and importance of visual information they capture. Today, broadcasting videos from camera phones uploaded by unknown users is admissible on news networks, and banking customers expect to be able to deposit checks using mobile devices. In this paper we introduce Movee, a system that addresses the fundamental question of whether the visual stream uploaded by a user has been captured live on a mobile device, and has not been tampered with by an adversary.Movee leverages the mobile device motion sensors and the intrinsic user movements during 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 unique strength of not depending on the audio track.We introduce novel attacks that focus on Movee's defenses, to fabricate acceleration data that mimics the motion observed in targeted videos. We use smartphones and wearable smart glasses to collect both genuine and attack data from 13 users. Our experiments show that Movee is able to efficiently detect human and automatically generated plagiarized videos: Movee's accuracy ranges between 68-93% on a smartphone, and between 76-91% on a Google Glass device.1536-1233 (c)