Do Digital Images Tell the Truth?

Since the advent of digital cameras, image editing tools have made it straightforward to manipulate content. Copy-move forgeries—where a region is duplicated and pasted within the same frame—are particularly challenging for human observers to detect, yet they threaten the credibility of visual evidence.

This book chapter surveys the state of the art in copy-move detection by analysing feature representations, learning strategies, and publicly available datasets. We catalogue low-level descriptors, machine learning pipelines, and deep architectures, and we discuss how each approach responds to common post-processing operations such as translation, rotation, and scaling. The chapter concludes with open challenges for building explainable and trustworthy forensic systems.