Deep Residual Network for Steganalysis of Digital Images
The DOI matches its Crossref record; 64 of the 64 references it cites were found in a registry or an index.
Abstract
Steganography detectors built as deep convolutional neural networks have firmly established themselves as superior to the previous detection paradigm - classifiers based on rich media models. Existing network architectures, however, still contain elements designed by hand, such as fixed or constrained convolutional kernels, heuristic initialization of kernels, the thresholded linear unit that mimics truncation in rich models, quantization of feature maps, and awareness of JPEG phase. In this work, we describe a deep residual architecture designed to minimize the use of heuristics and externally enforced elements that is universal in the sense that it provides state-of-the-art detection accuracy for both spatial-domain and JPEG steganography. The key part of the proposed architecture is a significantly expanded front part of the detector that “computes noise residuals” in which pooling has been disabled to prevent suppression of the stego signal. Extensive experiments show the superior performance of this network with a significant improvement, especially in the JPEG domain. Further performance boost is observed by supplying the selection channel as a second channel.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
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
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
(2010) · Cited by 14,134
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665 · cited 5×
“The shortcut connections help propagate gradients to upper layers, which are the hardest to train because of the vanishing gradient phenomenon [21] that often negatively affects the convergence and performance of deep architectures [26], [27].”
BackgroundMethodInfluentialBengio, 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×
“The detectors for all remaining payloads were built via curriculum training [5] with 50–100k iterations (57–114 epochs) with learning rate r1 and an additional 50k iterations (57 epochs) with the smaller learning rate r2.”
MethodADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513 · cited 1×
“1) Activations: Besides the ReLU, we have also experimented with TanH activation, the leaky ReLU, ELU [11], and SELU [36], but they did not bring any performance gain.”
MethodConvergence Results for Neural Networks via Electrodynamics
Panigrahy, R., Rahimi, A., Sachdeva, S., & Zhang, Q. (2018) · Leibniz international proceedings in informatics · doi:10.4230/lipics.itcs.2018.22 · Cited by 2,761
Self-Normalizing Neural Networks
Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.02515 · Cited by 2,267
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 3×
“initialized with SRM (Spatial Rich Model [19]) filters, and an effective way to incorporate the selection channel into the”
MethodSelf-citation”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
Self-citationEnsemble Classifiers for Steganalysis of Digital Media
Kodovsky, J., Fridrich, J., & Holub, V. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2011.2175919 · Cited by 1,064
Self-citationDesigning 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
Self-citationStructural 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
Deep Learning Hierarchical Representations for Image Steganalysis
Ye, J., Ni, J., & Yi, Y. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2710946 · Cited by 823
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
Self-citationA new cost function for spatial image steganography
Li, B., Wang, M., Huang, J., & Li, X. (2014) · 2014 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2014.7025854 · Cited by 632
Content-Adaptive Steganography by Minimizing Statistical Detectability
Sedighi, V., Cogranne, R., & Fridrich, J. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2486744 · Cited by 573
Self-citationSteganalysis 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
Low-Complexity Features for JPEG Steganalysis Using Undecimated DCT
Holub, V., & Fridrich, J. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2364918 · Cited by 430
Self-citationAutomatic Steganographic Distortion Learning Using a Generative Adversarial Network
Tang, W., Tan, S., Li, B., & Huang, J. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2745572 · Cited by 416
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
Self-citationA Markov Process Based Approach to Effective Attacking JPEG Steganography
Shi, Y. Q., Chen, C., & Chen, W. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-74124-4_17 · Cited by 344
Steganalysis of Adaptive JPEG Steganography Using 2D Gabor Filters
Song, X., Liu, F., Yang, C., Luo, X., & Zhang, Y. (2015) · Proceedings of the 3rd ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/2756601.2756608 · Cited by 300
Steganalysis of JPEG images using rich models
Kodovský, J., & Fridrich, J. (2012) · SPIE Proceedings · doi:10.1117/12.907495 · Cited by 297
Self-citationUniform Embedding for Efficient JPEG Steganography
Guo, L., Ni, J., & Shi, Y. Q. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2312817 · Cited by 294
Moving steganography and steganalysis from the laboratory into the real world
Ker, A. D., Bas, P., Böhme, R., Cogranne, R., Craver, S., Filler, T., Fridrich, J., & Pevný, T. (2013) · Proceedings of the first ACM workshop on Information hiding and multimedia security · doi:10.1145/2482513.2482965 · Cited by 244
Self-citationStacked convolutional auto-encoders for steganalysis of digital images
Tan, S., & Li, B. (2014) · Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific · doi:10.1109/apsipa.2014.7041565 · Cited by 230
Large-Scale JPEG Image Steganalysis Using Hybrid Deep-Learning Framework
Zeng, J., Tan, S., Li, B., & Huang, J. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2779446 · Cited by 226
Deep Convolutional Neural Network to Detect J-UNIWARD
Xu, G. (2017) · Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3082031.3083236 · Cited by 209
JPEG-Phase-Aware Convolutional Neural Network for Steganalysis of JPEG Images
Chen, M., Sedighi, V., Boroumand, M., & Fridrich, J. (2017) · Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3082031.3083248 · Cited by 176
Self-citationEnsemble 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
Steganalysis Features for Content-Adaptive JPEG Steganography
Denemark, T., Boroumand, M., & Fridrich, J. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2555281 · Cited by 171
Self-citationPhase-aware projection model for steganalysis of JPEG images
Holub, V., & Fridrich, J. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2075239 · Cited by 125
Self-citationAdaptive 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
Image steganalysis with binary similarity measures
Avcıbaş, İ., Memon, N. D., & Sankur, B. (2003) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2002.1039053 · Cited by 106
Adaptive Steganalysis Based on Embedding Probabilities of Pixels
Tang, W., Li, H., Luo, W., & Huang, J. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2507159 · Cited by 97
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
Statistical Model of Quantized DCT Coefficients: Application in the Steganalysis of Jsteg Algorithm
Thai, T. H., Cogranne, R., & Retraint, F. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2310126 · Cited by 82
Is ensemble classifier needed for steganalysis in high-dimensional feature spaces?
Cogranne, R., Sedighi, V., Fridrich, J., & Pevný, T. (2015) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs.2015.7368597 · Cited by 79
Self-citationSteganalysis of watermarking techniques using image quality metrics
Avcıbaş, İ., Memon, N. D., & Sankur, B. (2001) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.435436 · Cited by 66
Cogranne, R., & Fridrich, J. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2470220 · Cited by 65
Self-citationOn dangers of overtraining steganography to incomplete cover model
Kodovský, J., Fridrich, J., & Holub, V. (2011) · doi:10.1145/2037252.2037266 · Cited by 58
Self-citationCFA-aware features for steganalysis of color images
Goljan, M., & Fridrich, J. (2015) · SPIE Proceedings · doi:10.1117/12.2078399 · Cited by 57
Self-citationA Cover Image Model For Reliable Steganalysis
Cogranne, R., Zitzmann, C., Fillatre, L., Retraint, F., Nikiforov, I. V., & Cornu, P. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24178-9_13 · Cited by 53
Steganalysis Based on Awareness of Selection-Channel and Deep Learning
Yang, J., Liu, K., Kang, X., Wong, E., & Shi, Y.-Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-64185-0_20 · Cited by 34
Steganalysis via Deep Residual Network
Wu, S., Zhong, S.-H., & Liu, Y. (2016) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2016.0167 · Cited by 33
JPEG Steganalysis Based on DenseNetPreprint
Yang, J., Shi, Y.-Q., Wong, E. K., & Kang, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.09335 · Cited by 21
Towards dependable steganalysis
Pevný, T., & Ker, A. D. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083216 · Cited by 19
A Novel Mapping Scheme for Steganalysis
Chen, L., Shi, Y. Q., Sutthiwan, P., & Niu, X. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40099-5_3 · Cited by 16
Boosting Steganalysis with Explicit Feature Maps
Boroumand, M., & Fridrich, J. (2016) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2909827.2930803 · Cited by 12
Self-citationEffect of Imprecise Knowledge of the Selection Channel on Steganalysis
Sedighi, V., & Fridrich, J. (2015) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2756601.2756621 · Cited by 11
Self-citationNonlinear Feature Normalization in Steganalysis
Boroumand, M., & Fridrich, J. (2017) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3082031.3083239 · Cited by 10
Self-citation
Research works printed but not linked: 9
- 10.1007/978-3-642-36373-3_6 · doi:10.1007/978-3-642-36373-3_6
- fuji-tsang, 2018, Steganalyzing images of arbitrary size with CNNs, IS&T Electronic Imaging - Media Watermarking Security and Forensics, 121-1
- goodfellow, 2016, Deep Learning, 1
- 10.1145/3082031.3083243 · doi:10.1145/3082031.3083243
- 10.1109/WIFS.2014.7084324 · doi:10.1109/wifs.2014.7084324
- 10.2352/ISSN.2470-1173.2016.8.MWSF-080 · doi:10.2352/issn.2470-1173.2016.8.mwsf-080
- bas, 2007, BOWS-2
- böhme, 2010, Advanced Statistical Steganalysis, 10.1007/978-3-642-14313-7 · doi:10.1007/978-3-642-14313-7
- 10.1109/LSP.2010.2091127 · doi:10.1109/lsp.2010.2091127
Cited by
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
HiNet: Deep Image Hiding by Invertible Network
Jing, J., Deng, X., Xu, M., Wang, J., & Guan, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00469 · Cited by 356
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
An Embedding Cost Learning Framework Using GAN
Yang, J., Ruan, D., Huang, J., Kang, X., & Shi, Y.-Q. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2922229 · Cited by 268
DeepMIH: Deep Invertible Network for Multiple Image Hiding
Guan, Z., Jing, J., Deng, X., Xu, M., Jiang, L., Zhang, Z., & Li, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3141725 · Cited by 267
Metadata
- Authors
- Boroumand, M., Chen, M., & Fridrich, J.
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2019-05
- Volume
- 14
- Issue
- 5
- Pages
- 1181-1193
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2892948265
- Cited by
- 1,032
- References
- 64
- FWCI
- 31.40
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- National Science Foundation (1561446)
- Air Force Office of Scientific Research (FA9950-12-1-0124)
- Defense Advanced Research Projects Agency (FA8750-16-2-0173)
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.