Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels

2018/06/27 by Wei Wang, Jing Dong, Wang, Wei +5 · 1 citation
Computer Science · #Advanced Steganography and Watermarking Techniques #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis

paper · pdf · doi:10.48550/arxiv.1806.10443

openalex publication_date 2018/06/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recently, deep learning has shown its power in steganalysis. However, the proposed deep models have been often learned from pre-calculated noise residuals with fixed high-pass filters rather than from raw images. In this paper, we propose a new end-to-end learning framework that can learn steganalytic features directly from pixels. In the meantime, the high-pass filters are also automatically learned. Besides class labels, we make use of additional pixel level supervision of cover-stego image pair to jointly and iteratively train the proposed network which consists of a residual calculation network and a steganalysis network. The experimental results prove the effectiveness of the proposed architecture.

Cited by

• CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression

Related

• Deep Learning in steganography and steganalysis from 2015 to 2018
• CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images
• Steganalysis via a Convolutional Neural Network using Large Convolution Filters for Embedding Process with Same Stego Key
• Universal Deep Network for Steganalysis of Color Image based on Channel\n Representation
• Efficient feature learning and multi-size image steganalysis based on CNN