Preliminary Forensics Analysis of DeepFake Images
This addresses the issue of automated face manipulation in images and videos, which is a growing societal concern, but the work is preliminary and incremental.
The paper tackles the problem of detecting DeepFake images, particularly faces, by analyzing anomalies in the frequency domain, as standard forensic methods are insufficient, though no concrete results or numbers are provided.
One of the most terrifying phenomenon nowadays is the DeepFake: the possibility to automatically replace a person's face in images and videos by exploiting algorithms based on deep learning. This paper will present a brief overview of technologies able to produce DeepFake images of faces. A forensics analysis of those images with standard methods will be presented: not surprisingly state of the art techniques are not completely able to detect the fakeness. To solve this, a preliminary idea on how to fight DeepFake images of faces will be presented by analysing anomalies in the frequency domain.