Deep Residual Network for Steganalysis of Digital Images

• Published in: IEEE transactions on information forensics and security Vol. 14; no. 5; pp. 1181 - 1193
• Main Authors: Boroumand, Mehdi, Mo Chen, Fridrich, Jessica
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Architecture; Artificial neural networks; Convolution; convolutional neural network; deep residual network; Detectors; Digital imaging; Feature extraction; Feature maps; Image compression; JPEG encoders-decoders; Kernel; Kernels; Machine learning; selection channel; SRNet; State of the art; steganalysis; Steganography; Training; Transform coding
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2018.2871749

Steganography detectors built as deep convolutional neural networks have firmly established themselves as superior to the previous detection paradigm - classifiers based on rich media models. Existing network architectures, however, still contain elements designed by hand, such as fixed or constrained convolutional kernels, heuristic initialization of kernels, the thresholded linear unit that mimics truncation in rich models, quantization of feature maps, and awareness of JPEG phase. In this work, we describe a deep residual architecture designed to minimize the use of heuristics and externally enforced elements that is universal in the sense that it provides state-of-the-art detection accuracy for both spatial-domain and JPEG steganography. The key part of the proposed architecture is a significantly expanded front part of the detector that "computes noise residuals" in which pooling has been disabled to prevent suppression of the stego signal. Extensive experiments show the superior performance of this network with a significant improvement, especially in the JPEG domain. Further performance boost is observed by supplying the selection channel as a second channel.