Structural Design of Convolutional Neural Networks for Steganalysis

2016/03/30 by Guanshuo Xu, Hanzhou Wu, Han-Zhou Wu +1 · 15 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Digital Media Forensic Detection #Generative Adversarial Networks and Image Synthesis

paper · doi:10.1109/lsp.2016.2548421

openalex publication_date 2016/03/30 · crossref created 2016/03/30 · crossref issued 2016/05/01 · crossref published 2016/05/01 · crossref published-print 2016/05/01 · crossref deposited 2023/08/17 · openalex created_date 2025/10/10 · crossref indexed 2026/07/30 · openalex updated_date 2026/08/03

Abstract

Recent studies have indicated that the architectures of convolutional neural networks (CNNs) tailored for computer vision may not be best suited to image steganalysis. In this letter, we report a CNN architecture that takes into account knowledge of steganalysis. In the detailed architecture, we take absolute values of elements in the feature maps generated from the first convolutional layer to facilitate and improve statistical modeling in the subsequent layers; to prevent overfitting, we constrain the range of data values with the saturation regions of hyperbolic tangent (TanH) at early stages of the networks and reduce the strength of modeling using 1×1 convolutions in deeper layers. Although it learns from only one type of noise residual, the proposed CNN is competitive in terms of detection performance compared with the SRM with ensemble classifiers on the BOSSbase for detecting S-UNIWARD and HILL. The results have implied that well-designed CNNs have the potential to provide a better detection performance in the future.

Citations

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet classification with deep convolutional neural networks
• Deep Residual Learning for Image Recognition

Cited by

• Approximate Gaussian Mapping for Generative Image Steganography
• SemSteDiff: Generative Diffusion Model-based Coverless Semantic Steganography Communication
• Deep Data Hiding for ICAO-Compliant Face Images: A Survey
• CIF: A Constrained Inversion Framework for Reliable Message Extraction in Diffusion-Based Generative Steganography
• VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval
• Steganography Security: Principle and Practice
• Constructing feature variation coefficients to evaluate feature learning capabilities of convolutional layers in steganographic detection algorithms of spatial domain
• IStego100K: Large-scale Image Steganalysis Dataset
• Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization
• Video Forgery Detection for Surveillance Cameras: A Review
• Weakening the Detecting Capability of CNN-based Steganalysis
• F3SNet: A Four-Step Strategy for QIM Steganalysis of Compressed Speech Based on Hierarchical Attention Network
• Secure Intellicise Wireless Network: Agentic AI for Coverless Semantic Steganography Communication
• STCL:Curriculum learning Strategies for deep learning image steganography models
• GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security

Related

• Efficient feature learning and multi-size image steganalysis based on CNN
• Steganalysis via a Convolutional Neural Network using Large Convolution Filters for Embedding Process with Same Stego Key
• JPEG Steganalysis Based on DenseNet
• How to augment a small learning set for improving the performances of a CNN-based steganalyzer?
• Convolutional Neural Network Steganalysis's Application to Steganography