Detection of GAN-synthesized street videos
This addresses the emerging threat of non-facial AI-generated videos for security and media integrity, representing an incremental extension from facial deepfake detection.
The paper tackles the problem of detecting AI-generated street videos (DeepStreets), which lack existing detection tools unlike facial deepfakes, and presents a frame-based detector that achieves very good performance on state-of-the-art videos, including robustness to compression mismatches.
Research on the detection of AI-generated videos has focused almost exclusively on face videos, usually referred to as deepfakes. Manipulations like face swapping, face reenactment and expression manipulation have been the subject of an intense research with the development of a number of efficient tools to distinguish artificial videos from genuine ones. Much less attention has been paid to the detection of artificial non-facial videos. Yet, new tools for the generation of such kind of videos are being developed at a fast pace and will soon reach the quality level of deepfake videos. The goal of this paper is to investigate the detectability of a new kind of AI-generated videos framing driving street sequences (here referred to as DeepStreets videos), which, by their nature, can not be analysed with the same tools used for facial deepfakes. Specifically, we present a simple frame-based detector, achieving very good performance on state-of-the-art DeepStreets videos generated by the Vid2vid architecture. Noticeably, the detector retains very good performance on compressed videos, even when the compression level used during training does not match that used for the test videos.