Multimedia Forensics Before the Deep Learning Era

AbstractImage manipulation is as old as photography itself, and powerful media editing tools have been around for a long time. Using such conventional signal processing methods, it is possible to modify images and videos obtaining very realistic results. This chapter is devoted to describe the most effective strategies to detect the widespread manipulations that rely on traditional approaches and do not require a deep learning strategy. In particular, we will focus on manipulations like adding, replicating, or removing objects and present the major lines of research in multimedia forensics before the deep learning era and the rise of deepfakes. The most popular approaches look for artifacts related to the in-camera processing chain (camera-based clues) or the out-camera processing history (editing-based clues). We will focus on methods that rely on the extraction of a camera fingerprint and need some prior information on pristine data, for example, through a collection of images taken from the camera of interest. Then we will shift to blind methods that do not require any prior knowledge and reveal inconsistencies with respect to some well-defined hypotheses. We will also briefly review the most interesting features of machine learning- based methods and finally present the major challenges in this area.