Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

TL;DR

This paper introduces a CNN-based method that leverages JPEG DCT coefficients and image acquisition artifacts to improve the detection and localization of manipulated regions in images, outperforming existing techniques.

Contribution

The authors propose a novel neural network architecture, CAT-Net, capable of learning DCT coefficient distributions and jointly utilizing multiple artifact types for enhanced image manipulation detection.

Findings

CAT-Net significantly outperforms traditional methods.

Joint use of acquisition and compression artifacts improves accuracy.

The approach effectively localizes tampered regions in JPEG images.

Abstract

Detecting and localizing image manipulation are necessary to counter malicious use of image editing techniques. Accordingly, it is essential to distinguish between authentic and tampered regions by analyzing intrinsic statistics in an image. We focus on JPEG compression artifacts left during image acquisition and editing. We propose a convolutional neural network (CNN) that uses discrete cosine transform (DCT) coefficients, where compression artifacts remain, to localize image manipulation. Standard CNNs cannot learn the distribution of DCT coefficients because the convolution throws away the spatial coordinates, which are essential for DCT coefficients. We illustrate how to design and train a neural network that can learn the distribution of DCT coefficients. Furthermore, we introduce Compression Artifact Tracing Network (CAT-Net) that jointly uses image acquisition artifacts and compression artifacts. It significantly outperforms traditional and deep neural network-based methods in detecting and localizing tampered regions.