MesoNet: a Compact Facial Video Forgery Detection Network
This addresses the challenge of video face tampering detection for security and forensics applications, offering an efficient solution with incremental improvements over traditional methods.
The paper tackles the problem of detecting hyper-realistic forged videos like Deepfake and Face2Face by proposing MesoNet, a compact deep learning network focusing on mesoscopic properties, achieving detection rates of over 98% for Deepfake and 95% for Face2Face.
This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.