Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop.
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned.
This paper explores end-to-end optimization of the entire image acquisition and distribution workflow to facilitate reliable forensic analysis at the end of the distribution channel, where state-of-the-art forensic techniques fail.
Forensic analysis of digital photo provenance relies on intrinsic traces left in the photograph at the time of its acquisition.
We investigate if the random feature selection approach proposed in  to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features.