Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images
This addresses forensic analysis for deepfake detection, but it is incremental as it builds on existing knowledge of patterns in synthetic images.
The paper tackles the problem of detecting how many times a digital image has been processed by generative architectures for style transfer, proposing a first approach to investigate image ballistics on deepfake images subject to such manipulations.
Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synthetic images contain patterns that can determine not only if it is a deepfake but also the generative architecture employed to create the image data itself. These traces can be exploited to study problems that have never been addressed in the context of deepfakes. To this aim, in this paper a first approach to investigate the image ballistics on deepfake images subject to style-transfer manipulations is proposed. Specifically, this paper describes a study on detecting how many times a digital image has been processed by a generative architecture for style transfer. Moreover, in order to address and study accurately forensic ballistics on deepfake images, some mathematical properties of style-transfer operations were investigated.