Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images

TL;DR

This paper investigates the forensic analysis of deepfake images, focusing on detecting multiple style-transfer manipulations and exploring mathematical properties of style-transfer operations to improve deepfake forensics.

Contribution

It introduces a novel approach to forensic ballistics on deepfake images, analyzing multiple processing steps and mathematical properties of style-transfer techniques.

Findings

Detected multiple style-transfer manipulations in deepfake images.

Identified mathematical properties relevant to forensic analysis.

Provided insights into the traceability of generative architectures.

Abstract

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.