Abstract
Current steganalyzers based on deep learning mostly adopt wider or deeper designs to improve detection performance. However, an overly complex network increases the training cost and is not conducive to its expansion and optimization. Moreover, steganalysis pays more attention to high-frequency information corresponding to the image texture. However, the deeper the network, the more likely it is to learn low-frequency information corresponding to the image content, which is inconsistent with the goal of steganalysis. In response to these problems, a multi-frequency residual deep convolutional neural network for steganalysis of color images called MFRNet is proposed in this paper. We apply the idea of multi-frequency analysis to steganography detection for the first time, effectively controlling the network scale. By designing columns of different depths, it can learn different frequency components of steganographic noise at the same time. The detection performance is better than the existing networks that only learn a single frequency component of steganographic noise at the same depth. Therefore, it can achieve a good detection performance with a lighter architecture. In addition, by designing residual basic blocks with different residual shortcuts, different scales of steganographic noise residuals can be calculated at the same time, which can effectively suppress the interference of image content, so as to better reduce the impact of steganography algorithm mismatch and payload mismatch than the existing methods. The experimental results on PPG-LIRMM-COLOR showed that the proposed MFRNet outperformed the state-of-the-art model WISERNet.
Highlights
Steganography and steganography have always been a focus of research in the field of information hiding in recent years
We found that the existing steganalysis network based on deep learning generally has the following problems: First, in order to improve the detection performance, the networks are usually designed too deep or too wide
In order to solve the above problems, we introduce the idea of multi-frequency residual analysis into steganalysis, and a residual steganalysis convolutional neural network called MFRNet based on multi-frequency residual analysis suitable for color images is proposed
Summary
Steganography and steganography have always been a focus of research in the field of information hiding in recent years. The steganalysis algorithm based on deep learning can automatically learn steganographic features through network training, and simultaneously perform feature extraction and classifier optimization. It can avoid the dependence of traditional manual extraction of features on experience and become a new development trend of steganalysis [12]. Further suppressing the interference of image content, and comprehensively learning the steganographic noise residual components of different frequencies and different scales, and improving the detection performance on images with small payload. This effectively improves the detection ability of the network model in the case of small payloads. The network proposed in this paper is mainly compared with the state-of-the-art model WISERNet 。 Section IV gives conclusions and future research directions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
