{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:21:53Z","timestamp":1775578913207,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T00:00:00Z","timestamp":1683936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China","award":["62002214"],"award-info":[{"award-number":["62002214"]}]},{"name":"Natural Science Foundation of China","award":["U1936214"],"award-info":[{"award-number":["U1936214"]}]},{"name":"Natural Science Foundation of China","award":["22CG49"],"award-info":[{"award-number":["22CG49"]}]},{"name":"Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission","award":["62002214"],"award-info":[{"award-number":["62002214"]}]},{"name":"Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission","award":["U1936214"],"award-info":[{"award-number":["U1936214"]}]},{"name":"Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission","award":["22CG49"],"award-info":[{"award-number":["22CG49"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Deep neural networks have achieved remarkable success in various fields of artificial intelligence. However, these models, which contain a large number of parameters, are widely distributed and disseminated by researchers, engineers, and even unauthorized users. Except for intelligent tasks, typically overparameterized deep neural networks have become new digital covers for data hiding, which may pose significant security challenges to AI systems. To address this issue, this paper proposes a symmetric steganalysis scheme specifically designed for neural networks trained for image classification tasks. The proposed method focuses on detecting the presence of additional data without access to the internal structure or parameters of the host network. It employs a well-designed method based on histogram distribution to find the optimal decision threshold, with a symmetric determining rule where the original networks and stego networks undergo two highly symmetrical flows to generate the classification labels; the method has been shown to be practical and effective. SVM and ensemble classifiers were chosen as the binary classifier for their applicability to feature vectors output from neural networks based on different datasets and network structures. This scheme is the first of its kind, focusing on steganalysis for neural networks based on the distribution of network output, compared to conventional digital media such as images, audio, and video. Overall, the proposed scheme offers a promising approach to enhancing the security of deep neural networks against data hiding attacks.<\/jats:p>","DOI":"10.3390\/sym15051079","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T08:28:16Z","timestamp":1684139296000},"page":"1079","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Steganalysis of Neural Networks Based on Symmetric Histogram Distribution"],"prefix":"10.3390","volume":"15","author":[{"given":"Xiong","family":"Tang","sequence":"first","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0283-5338","authenticated-orcid":false,"given":"Zichi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China"}]},{"given":"Xinpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shehab, D.A., and Alhaddad, M.J. (2022). Comprehensive Survey of Multimedia Steganalysis: Techniques, Evaluations, and Trends in Future Research. Symmetry, 14.","DOI":"10.3390\/sym14010117"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.patcog.2003.08.007","article-title":"Hiding data in images by simple LSB substitution","volume":"37","author":"Chan","year":"2004","journal-title":"Pattern Recognit."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/LSP.2006.870357","article-title":"LSB matching revisited","volume":"13","author":"Mielikainen","year":"2006","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_4","unstructured":"Pevn\u00fd, T., Filler, T., and Bas, P. (2010). Proceedings of the International Workshop on Information Hiding, Springer."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Holub, V., and Fridrich, J. (2012, January 2\u20135). Designing steganographic distortion using directional filters. Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security (WIFS), Costa Adeje, Spain.","DOI":"10.1109\/WIFS.2012.6412655"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Holub, V., and Fridrich, J. (2013, January 17\u201319). Digital image steganography using universal distortion. Proceedings of the 1st ACM Workshop on Information Hiding and Multimedia Security, Montpellier, France.","DOI":"10.1145\/2482513.2482514"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TIFS.2014.2326954","article-title":"Investigation on cost assignment in spatial image steganography","volume":"9","author":"Li","year":"2014","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1109\/TIFS.2011.2134094","article-title":"Minimizing additive distortion in steganography using syndrome-trellis codes","volume":"6","author":"Filler","year":"2011","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.1109\/LSP.2017.2745572","article-title":"Automatic steganographic distortion learning using a generative adversarial network","volume":"24","author":"Tang","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhu, J., Kaplan, R., Johnson, J., and Li, F.-F. (2018, January 8\u201314). Hidden: Hiding data with deep networks. Proceedings of the The European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01267-0_40"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lin, J., Chang, C.-C., and Horng, J.-H. (2021). Asymmetric Data Hiding for Compressed Images with High Payload and Reversibility. Symmetry, 13.","DOI":"10.3390\/sym13122355"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1685","DOI":"10.1109\/TPAMI.2019.2901877","article-title":"Hiding images within images","volume":"42","author":"Baluja","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_13","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G. (2012, January 3\u20136). Imagenet classification with deep convolutional networks. Proceedings of the Neural Information Processing Systems (NIPS), Lake Tahoe, NV, USA."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1109\/LSP.2019.2895967","article-title":"Unconstrained offline handwritten word recognition by position embedding integrated ResNets model","volume":"26","author":"Wu","year":"2019","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_15","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017, January 4\u20139). Dynamic routing between capsules. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","article-title":"Generative adversarial networks: An overview","volume":"35","author":"Creswell","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Uchida, Y., Nagai, Y., Sakazawa, S., and Satoh, S. (2017, January 6\u20139). Embedding watermarks into deep neural networks. Proceedings of the ACM on International Conference Multimedia Retrieval, Bucharest, Romania.","DOI":"10.1145\/3078971.3078974"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MCI.2021.3108305","article-title":"Data Hiding in Neural Networks for Multiple Receivers","volume":"16","author":"Wang","year":"2021","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_19","first-page":"1","article-title":"Watermarking in deep neural networks via error back-propagation","volume":"2020","author":"Wang","year":"2020","journal-title":"Electron. Imag."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, J., Gu, Z., Jang, J., and Wu, H. (2018, January 4\u20138). Protecting intellectual property of deep neural networks with watermarking. Proceedings of the 2018 Asia Conference on Computer and Communications Security, Incheon, Republic of Korea.","DOI":"10.1145\/3196494.3196550"},{"key":"ref_21","unstructured":"Adi, Y., Baum, C., Cisse, M., Pinkas, B., and Keshet, J. (2018, January 15\u201317). Turning your weakness into a strength: Watermarking deep neural networks by backdooring. Proceedings of the 27th {USENIX} Security Symposium, ({USENIX} Security 18), Baltimore, MD, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9233","DOI":"10.1007\/s00521-019-04434-z","article-title":"Adversarial frontier stitching for remote neural network watermarking","volume":"32","author":"Merrer","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1109\/TCSVT.2020.3030671","article-title":"Watermarking neural networks with watermarked images","volume":"31","author":"Wu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1109\/TIFS.2006.879281","article-title":"Matrix embedding for large payloads","volume":"1","author":"Fridrich","year":"2006","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1109\/TCSVT.2021.3057599","article-title":"Repeatable Data Hiding: Towards the Reusability of Digital Images","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TCSVT.2018.2881118","article-title":"Towards Robust Image Steganography","volume":"29","author":"Tao","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_27","unstructured":"Simmons, G.J. (1984). Advance in Cryptology, Springer."},{"key":"ref_28","unstructured":"Chandramouli, R., and Memon, N. (2001, January 7\u201310). Analysis of LSB based image steganography techniques. Proceedings of the 2001 International Conference on Image Processing (Cat. No.01CH37205), Thessaloniki, Greece."},{"key":"ref_29","unstructured":"(2003, January 20). Higher-order statistical steganalysis of palette images. Proceedings of the SPIE Security Watermarking Multimedia Contents, Santa Clara, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/LSP.2005.847889","article-title":"Steganalysis of LSB matching in grayscale images","volume":"12","author":"Ker","year":"2005","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Tang, W., Li, H., Luo, W., and Huang, J. (2014). Adaptive Steganalysis against WOW Embedding Algorithm, ACM.","DOI":"10.1145\/2600918.2600935"},{"key":"ref_32","unstructured":"Shi, Y.Q., Chen, C., and Wen, C. (2006, January 10\u201312). A Markov Process Based Approach to Effective Attacking JPEG Steganography. Proceedings of the Information Hiding, 8th International Workshop, IH 2006, Alexandria, VA, USA."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/TIFS.2008.2002936","article-title":"Multiclass Detector of Current Steganographic Methods for JPEG Format","volume":"3","author":"Pevny","year":"2008","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1109\/TIFS.2012.2190402","article-title":"Rich Models for Steganalysis of Digital Images","volume":"7","author":"Fridrich","year":"2012","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/TCSVT.2019.2891778","article-title":"Diversity-Based Cascade Filters for JPEG Steganalysis","volume":"30","author":"Feng","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/LSP.2016.2548421","article-title":"Structural Design of Convolutional Neural Networks for Steganalysis","volume":"23","author":"Xu","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yedroudj, M., Comby, F., and Chaumont, M. (2018). Yedroudj-Net: An efficient CNN for spatial steganalysis. arXiv.","DOI":"10.1109\/ICASSP.2018.8461438"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1109\/TIFS.2018.2871749","article-title":"Deep Residual Network for Steganalysis of Digital Images","volume":"14","author":"Boroumand","year":"2019","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1109\/TIFS.2019.2936913","article-title":"Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis","volume":"15","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","article-title":"Least squares support vector machine classifiers","volume":"9","author":"Suykens","year":"1999","journal-title":"Neural Process. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1109\/TIFS.2011.2175919","article-title":"Ensemble Classifiers for Steganalysis of Digital Media","volume":"7","author":"Kodovsky","year":"2012","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Bas, P., Filler, T., and Pevn\u00fd, T. (2011). Proceedings of the International Workshop on Information Hiding, Springer.","DOI":"10.1007\/978-3-642-24178-9"},{"key":"ref_45","unstructured":"Bas, P., and Furon, T. (2007\u201317, January 17). BOWS-2 Contest (Break Our Watermarking System). Proceedings of the European Network of Excellence ECRYPT, Virtual."},{"key":"ref_46","unstructured":"LeCun, Y., Cortes, C., and Burges, C.J. (2023, May 11). The MNIST Database of Handwritten Digits. Available online: http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_47","unstructured":"Krizhevsky, A. (2023, May 11). Learning Multiple Layers of Features from Tiny Images. Technical Report, CIFAR. Available online: https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf."},{"key":"ref_48","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/5\/1079\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:34:17Z","timestamp":1760124857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/5\/1079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,13]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["sym15051079"],"URL":"https:\/\/doi.org\/10.3390\/sym15051079","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,13]]}}}