Deep Learning Hierarchical Representations for Image Steganalysis
The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Nowadays, the prevailing detectors of steganographic communication in digital images mainly consist of three steps, i.e., residual computation, feature extraction, and binary classification. In this paper, we present an alternative approach to steganalysis of digital images based on convolutional neural network (CNN), which is shown to be able to well replicate and optimize these key steps in a unified framework and learn hierarchical representations directly from raw images. The proposed CNN has a quite different structure from the ones used in conventional computer vision tasks. Rather than a random strategy, the weights in the first layer of the proposed CNN are initialized with the basic high-pass filter set used in the calculation of residual maps in a spatial rich model (SRM), which acts as a regularizer to suppress the image content effectively. To better capture the structure of embedding signals, which usually have extremely low SNR (stego signal to image content), a new activation function called a truncated linear unit is adopted in our CNN model. Finally, we further boost the performance of the proposed CNN-based steganalyzer by incorporating the knowledge of selection channel. Three state-of-the-art steganographic algorithms in spatial domain, e.g., WOW, S-UNIWARD, and HILL, are used to evaluate the effectiveness of our model. Compared to SRM and its selection-channel-aware variant maxSRMd2, our model achieves superior performance across all tested algorithms for a wide variety of payloads.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
(2010) · Cited by 14,134
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
(2011) · Cited by 6,993
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“In our work, however, the issue above can be well solved by adopting a curriculum learning [26] or transfer learning strategy [27].”
BackgroundADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.5093 · Cited by 3,752
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Rich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · cited 5×
“domain are the Spatial Rich Model (SRM) [4] and its several variants [5], [6].”
BackgroundMethodInfluential”Break Our Steganographic System”: The Ins and Outs of Organizing BOSS
Bas, P., Filler, T., & Pevný, T. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24178-9_5 · Cited by 1,250
Universal distortion function for steganography in an arbitrary domain
Holub, V., Fridrich, J., & Denemark, T. (2014) · EURASIP Journal on Information Security · doi:10.1186/1687-417x-2014-1 · Cited by 1,202
Using High-Dimensional Image Models to Perform Highly Undetectable Steganography
Pevný, T., Filler, T., & Bas, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-16435-4_13 · Cited by 1,009
Designing steganographic distortion using directional filters
Holub, V., & Fridrich, J. (2012) · 2012 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2012.6412655 · Cited by 966
Steganalysis by Subtractive Pixel Adjacency Matrix
Pevny, T., Bas, P., & Fridrich, J. (2010) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2010.2045842 · Cited by 887
Structural Design of Convolutional Neural Networks for Steganalysis
Xu, G., Wu, H.-Z., & Shi, Y.-Q. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2548421 · Cited by 840
Steganalysis by subtractive pixel adjacency matrix
Pevný, T., Bas, P., & Fridrich, J. (2009) · Proceedings of the 11th ACM workshop on Multimedia and security · doi:10.1145/1597817.1597831 · Cited by 769
Steganalysis using image quality metrics
Avcibas, I., Memon, N., & Sankur, B. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2002.807363 · Cited by 562
Deep learning for steganalysis via convolutional neural networks
Qian, Y., Dong, J., Wang, W., & Tan, T. (2015) · SPIE Proceedings · doi:10.1117/12.2083479 · Cited by 537
Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines
Lyu, S., & Farid, H. (2003) · Lecture Notes in Computer Science · doi:10.1007/3-540-36415-3_22 · Cited by 450
Selection-channel-aware rich model for Steganalysis of digital images
Denemark, T., Sedighi, V., Holub, V., Cogranne, R., & Fridrich, J. (2014) · 2014 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2014.7084302 · Cited by 375
New blind steganalysis and its implications
Goljan, M., Fridrich, J., & Holotyak, T. (2006) · SPIE Proceedings · doi:10.1117/12.643254 · Cited by 265
Random Projections of Residuals for Digital Image Steganalysis
Holub, V., & Fridrich, J. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2286682 · Cited by 261
Learning and transferring representations for image steganalysis using convolutional neural network
Qian, Y., Dong, J., Wang, W., & Tan, T. N. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532860 · Cited by 183
Ensemble of CNNs for Steganalysis: An Empirical Study
Xu, G., Wu, H., & Shi, Y. Q. (2016) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2909827.2930798 · Cited by 172
Pibre, L., Pasquet, J., Ienco, D., & Chaumont, M. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.8.mwsf-078 · Cited by 164
Adaptive steganalysis against WOW embedding algorithm
Tang, W., Li, H., Luo, W., & Huang, J. (2014) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2600918.2600935 · Cited by 115
Steganalysis based on Markov Model of Thresholded Prediction-Error Image
Zou, D., Shi, Y. B., Su, W., & Xuan, G. (2006) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2006.262792 · Cited by 90
Cited by
Deep Residual Network for Steganalysis of Digital Images
Boroumand, M., Chen, M., & Fridrich, J. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2871749 · Cited by 1,032
Zhang, R., Zhu, F., Liu, J., & Liu, G. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2936913 · Cited by 420
A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks
Hu, D., Wang, L., Jiang, W., Zheng, S., & Li, B. (2018) · IEEE Access · doi:10.1109/access.2018.2852771 · Cited by 342
Yedroudj-Net: An Efficient CNN for Spatial Steganalysis
Yedroudj, M., Comby, F., & Chaumont, M. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461438 · Cited by 303
A Siamese CNN for Image Steganalysis
You, W., Zhang, H., & Zhao, X. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3013204 · Cited by 297
Metadata
- Authors
- Ye, J., Ni, J., & Yi, Y.
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2017-11
- Volume
- 12
- Issue
- 11
- Pages
- 2545-2557
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2621048556
- Cited by
- 823
- References
- 31
- FWCI
- 23.47
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.