Yedroudj-Net: An Efficient CNN for Spatial Steganalysis

Abstract

For about 10 years, detecting the presence of a secret message hidden in an image was performed with an Ensemble Classifier trained with Rich features. In recent years, studies such as Xu et al. have indicated that well-designed convolutional Neural Networks (CNN) can achieve comparable performance to the two-step machine learning approaches.In this paper, we propose a CNN that outperforms the state-ofthe-art in terms of error probability. The proposition is in the continuity of what has been recently proposed and it is a clever fusion of important bricks used in various papers. Among the essential parts of the CNN, one can cite the use of a pre-processing filterbank and a Truncation activation function, five convolutional layers with a Batch Normalization associated with a Scale Layer, as well as the use of a sufficiently sized fully connected section. An augmented database has also been used to improve the training of the CNN.Our CNN was experimentally evaluated against S-UNIWARD and WOW embedding algorithms and its performances were compared with those of three other methods: an Ensemble Classifier plus a Rich Model, and two other CNN steganalyzers.

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

“…It performs slightly better than PSRM [27]. Yedroudj-Net et al [23], proposed CNN framework that outperforms in term of the error probability. Experiments were performed to show its supremacy with other state-of the art framework like Xu-net [35], & Ye-Net [28] in its not informed version and to Ensemble Classifier fed by the Spatial Rich Model [33].…”

“…Experiments were performed to show its supremacy with other state-of the art framework like Xu-net [35], & Ye-Net [28] in its not informed version and to Ensemble Classifier fed by the Spatial Rich Model [33]. In 2018, Zhang et al [10], proposed an adequate feature learning & multi-size image steganalysis framework based on CNN called Zhu-net and the proposed network achieved better detection performance compared to Yedrouudj-Net [23]. Zhu-Net offer three improvement in Yedroudj-Net that are the renovate the kernel filters of pre-processinglayer, secondly replace the first two convolutional blocks with two module of depth-wise detachable convolutions that can extract the spatial and channel correlation of residuals to increase SNR and obviously improve the accuracy, finally replace the gobal pooling with spatial pyramid pooling to deal with arbitrary images.…”

“…Best CNN framework for JPEG as well as spatial steganalysis at the end of 2018 is SR-Net that has been proposed with side-channel-information [8]. The network is corresponding to the combination of convolutional blocks beyond the pooling layer immediately after the first convolution block of the Yedrouj-Net [23]. Essential part of SR-Net is noise residual extraction section consist of first seven layers.…”

CNN-Based Ternary Classification for Image Steganalysis

“…The SRM is highly accurate compared to CNN-based methods. The method of extracting many features using various types of HPFs has also been widely used in CNN-based ones [19,20,[25][26][27]].…”

“…With the great success of convolutional neural networks (CNN) in object detection and recognition [15,16], using CNNs for steganalysis has been actively investigated [17][18][19][20][21][22][23][24][25][26][27]. Unlike handcrafted feature-based methods, a CNN can automatically extract and learn the features that are optimal or well suited for identifying steganographic methods.…”