Splicing Detection and Localization In Satellite Imagery Using Conditional GANs

TL;DR

This paper introduces a method using Conditional GANs to detect and localize splicing forgeries in satellite imagery, addressing the challenge of verifying image integrity in digital forensics.

Contribution

The paper presents a novel application of cGANs for detecting and localizing image splicing in satellite images, a new approach in digital image forensics.

Findings

High success rate in detecting spliced regions

Effective localization of forgery shapes

Applicable to various types of satellite image manipulations

Abstract

The widespread availability of image editing tools and improvements in image processing techniques allow image manipulation to be very easy. Oftentimes, easy-to-use yet sophisticated image manipulation tools yields distortions/changes imperceptible to the human observer. Distribution of forged images can have drastic ramifications, especially when coupled with the speed and vastness of the Internet. Therefore, verifying image integrity poses an immense and important challenge to the digital forensic community. Satellite images specifically can be modified in a number of ways, including the insertion of objects to hide existing scenes and structures. In this paper, we describe the use of a Conditional Generative Adversarial Network (cGAN) to identify the presence of such spliced forgeries within satellite images. Additionally, we identify their locations and shapes. Trained on pristine and falsified images, our method achieves high success on these detection and localization objectives.