On Detecting GANs and Retouching based Synthetic Alterations

TL;DR

This paper introduces a CNN-based method for detecting both retouched and GAN-generated images, achieving over 99% accuracy and surpassing previous techniques, thereby addressing a critical challenge in digital image forensics.

Contribution

The paper presents a novel supervised deep learning approach that effectively detects synthetic image alterations and GAN-generated images, outperforming existing methods.

Findings

Achieved 99.65% accuracy in detecting retouched images.

Achieved 99.83% accuracy in identifying GAN-generated images.

Outperformed previous state-of-the-art accuracy of 87%.

Abstract

Digitally retouching images has become a popular trend, with people posting altered images on social media and even magazines posting flawless facial images of celebrities. Further, with advancements in Generative Adversarial Networks (GANs), now changing attributes and retouching have become very easy. Such synthetic alterations have adverse effect on face recognition algorithms. While researchers have proposed to detect image tampering, detecting GANs generated images has still not been explored. This paper proposes a supervised deep learning algorithm using Convolutional Neural Networks (CNNs) to detect synthetically altered images. The algorithm yields an accuracy of 99.65% on detecting retouching on the ND-IIITD dataset. It outperforms the previous state of the art which reported an accuracy of 87% on the database. For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99.83%.