2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018
DOI: 10.1109/icassp.2018.8461438
|View full text |Cite
|
Sign up to set email alerts
|

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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
176
0
2

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 220 publications
(180 citation statements)
references
References 22 publications
2
176
0
2
Order By: Relevance
“…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].…”
Section: Spatial Steganalysis Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…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].…”
Section: Spatial Steganalysis Methodsmentioning
confidence: 99%
“…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.…”
Section: Spatial Steganalysis Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…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]].…”
Section: Srmmentioning
confidence: 99%
“…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.…”
Section: Introductionmentioning
confidence: 99%