论文标题
从外观和行为中检测深摄影视频
Detecting Deep-Fake Videos from Appearance and Behavior
论文作者
论文摘要
合成生成的音频和视频（所谓的深色假货）继续捕捉到计算机图和计算机视觉社区的想象力。同时，访问技术的民主化，可以创建任何人说任何事情的复杂操纵视频，因为它有能力破坏民主选举，对大规模欺诈，燃料不明信息的运动和创造非自愿性色情。我们描述了一种基于生物识别的取证技术，用于检测面部塑料深色的伪造。该技术将基于面部识别的静态生物识别与基于面部表情和头部运动的时间性行为生物识别结合在一起，其中使用具有度量学习目标函数的CNN学习了行为嵌入。我们显示了这种方法在几个大型视频数据集以及野外深色假货中的功效。
Synthetically-generated audios and videos -- so-called deep fakes -- continue to capture the imagination of the computer-graphics and computer-vision communities. At the same time, the democratization of access to technology that can create sophisticated manipulated video of anybody saying anything continues to be of concern because of its power to disrupt democratic elections, commit small to large-scale fraud, fuel dis-information campaigns, and create non-consensual pornography. We describe a biometric-based forensic technique for detecting face-swap deep fakes. This technique combines a static biometric based on facial recognition with a temporal, behavioral biometric based on facial expressions and head movements, where the behavioral embedding is learned using a CNN with a metric-learning objective function. We show the efficacy of this approach across several large-scale video datasets, as well as in-the-wild deep fakes.
