Lightweight Steganography Detection Method Based on Multiple Residual Structures and Transformer  

作　　者：Hao LI Yi ZHANG Jinwei WANG Weiming ZHANG Xiangyang LUO 

机构地区：[1]Key Laboratory of Cyberspace Situation Awareness of Henan Province,Zhengzhou 450001,China [2]Nanjing University of Information Science&Technology,Nanjing 210044,China [3]University of Science and Technology of China,Hefei 230052,China

出　　处：《Chinese Journal of Electronics》2024年第4期965-978,共14页电子学报（英文版）

基　　金：National Natural Science Foundation of China (Grant Nos. 62172435, 62202495, and U2336206);National Key Research and Development Program of China (Grant No. 2022 YFB3102900);Zhongyuan Science and Technology Innovation Leading Talent Project, China (Grant No. 214200510019);Key Research and Development Project of Henan Province (Grant No. 221111321200)。

摘　　要：Existing deep learning-based steganography detection methods utilize convolution to automatically capture and learn steganographic features, yielding higher detection efficiency compared to manually designed steganography detection methods. Detection methods based on convolutional neural network frameworks can extract global features by increasing the network's depth and width. These frameworks are not highly sensitive to global features and can lead to significant resource consumption. This manuscript proposes a lightweight steganography detection method based on multiple residual structures and Transformer(Res Former). A multi-residuals block based on channel rearrangement is designed in the preprocessing layer. Multiple residuals are used to enrich the residual features and channel shuffle is used to enhance the feature representation capability. A lightweight convolutional and Transformer feature extraction backbone is constructed, which reduces the computational and parameter complexity of the network by employing depth-wise separable convolutions. This backbone integrates local and global image features through the fusion of convolutional layers and Transformer, enhancing the network's ability to learn global features and effectively enriching feature diversity. An effective weighted loss function is introduced for learning both local and global features, Bias Loss loss function is used to give full play to the role of feature diversity in classification, and cross-entropy loss function and contrast loss function are organically combined to enhance the expression ability of features. Based on Boss Base-1.01, BOWS2 and ALASKA#2, extensive experiments are conducted on the stego images generated by spatial and JPEG domain adaptive steganographic algorithms, employing both classical and state-of-theart steganalysis techniques. The experimental results demonstrate that compared to the SRM, SRNet, Sia Steg Net,CSANet, LWENet, and Sia IRNet methods, the proposed Res Former method achieves the highest reduction in

关 键 词：STEGANALYSIS Multiple residual blocks Transformer Channel shuffle 

分 类 号：TP309[自动化与计算机技术—计算机系统结构] TP18[自动化与计算机技术—计算机科学与技术] TM41[电气工程—电器]