{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:21:12Z","timestamp":1780762872330,"version":"3.54.1"},"reference-count":30,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2020,2,8]],"date-time":"2020-02-08T00:00:00Z","timestamp":1581120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Image watermarking is usually decomposed into three steps: (i) a feature vector is extracted from an image; (ii) it is modified to embed the watermark; (iii) and it is projected back into the image space while avoiding the creation of visual artefacts. This feature extraction is usually based on a classical image representation given by the Discrete Wavelet Transform or the Discrete Cosine Transform for instance. These transformations require very accurate synchronisation between the embedding and the detection and usually rely on various registration mechanisms for that purpose. This paper investigates a new family of transformation based on Deep Neural Networks trained with supervision for a classification task. Motivations come from the Computer Vision literature, which has demonstrated the robustness of these features against light geometric distortions. Also, adversarial sample literature provides means to implement the inverse transform needed in the third step above mentioned. As far as zero-bit watermarking is concerned, this paper shows that this approach is feasible as it yields a good quality of the watermarked images and an intrinsic robustness. We also tests more advanced tools from Computer Vision such as aggregation schemes with weak geometry and retraining with a dataset augmented with classical image processing attacks.<\/jats:p>","DOI":"10.3390\/e22020198","type":"journal-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T11:48:51Z","timestamp":1581335331000},"page":"198","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Are Classification Deep Neural Networks Good for Blind Image Watermarking?"],"prefix":"10.3390","volume":"22","author":[{"given":"Vedran","family":"Vukoti\u0107","sequence":"first","affiliation":[{"name":"Lamark, 35000 Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivien","family":"Chappelier","sequence":"additional","affiliation":[{"name":"Lamark, 35000 Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1565-765X","authenticated-orcid":false,"given":"Teddy","family":"Furon","sequence":"additional","affiliation":[{"name":"INRIA, CNRS, IRISA, University of Rennes, 35000 Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Commun. ACM, 60.","DOI":"10.1145\/3065386"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sim\u00e9oni, O., Iscen, A., Tolias, G., Avrithis, Y., and Chum, O. (2018, January 12\u201315). Unsupervised object discovery for instance recognition. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV 2018), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00194"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wu, J., Yu, Y., Huang, C., and Yu, K. (2015, January 7\u201312). Deep multiple instance learning for image classification and auto-annotation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., Furon, T., and Chum, O. (2017, January 6\u20139). Panorama to Panorama Matching for Location Recognition. Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR 2017), Bucharest, Romania.","DOI":"10.1145\/3078971.3079033"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples. Computer Vision\u2014ECCV 2016, Springer.","DOI":"10.1007\/978-3-319-46454-1"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Deep image retrieval: Learning global representations for image search. Computer Vision \u2013 ECCV 2016, Springer.","DOI":"10.1007\/978-3-319-46487-9"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kanbak, C., Moosavi-Dezfooli, S.M., and Frossard, P. (2017). Geometric robustness of deep networks: Analysis and improvement. arXiv.","DOI":"10.1109\/CVPR.2018.00467"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s13735-018-0147-1","article-title":"Digital watermarking for deep neural networks","volume":"7","author":"Nagai","year":"2018","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Darvish Rouhani, B., Chen, H., and Koushanfar, F. (2018). DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models. arXiv.","DOI":"10.1145\/3297858.3304051"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1016\/S0165-1684(00)00239-5","article-title":"Digital watermarking based on neural networks for color images","volume":"81","author":"Yu","year":"2001","journal-title":"Signal Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1016\/j.patcog.2008.01.007","article-title":"Machine learning based adaptive watermark decoding in view of anticipated attack","volume":"41","author":"Khan","year":"2008","journal-title":"Pattern Recognit."},{"key":"ref_12","first-page":"61","article-title":"Improving digital watermarking fidelity using fast neural network for adaptive wavelet synthesis","volume":"18","author":"Stolarek","year":"2010","journal-title":"J. Appl. Comput. Sci."},{"key":"ref_13","unstructured":"Mun, S., Nam, S., Jang, H., Kim, D., and Lee, H. (2017). A Robust Blind Watermarking Using Convolutional Neural Network. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). HiDDeN: Hiding Data With Deep Networks. Computer Vision\u2013ECCV 2018, Springer.","DOI":"10.1007\/978-3-030-01228-1"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Quiring, E., Arp, D., and Rieck, K. (2018, January 24\u201326). Forgotten siblings: Unifying attacks on machine learning and digital watermarking. Proceedings of the 2018 IEEE European Symposium on Security and Privacy, London, UK.","DOI":"10.1109\/EuroSP.2018.00041"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Vukoti\u0107, V., Chappelier, V., and Furon, T. (2018, January 11\u201313). Are Deep Neural Networks good for blind image watermarking?. Proceedings of the 2018 IEEE International Workshop on Information Forensics and Security (WIFS), Hong Kong, China.","DOI":"10.1109\/WIFS.2018.8630768"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1109\/TIT.2007.911210","article-title":"Optimal watermark embedding and detection strategies under limited detection resources","volume":"54","author":"Merhav","year":"2008","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"597040","DOI":"10.1155\/2008\/597040","article-title":"Broken Arrows","volume":"2008","author":"Furon","year":"2008","journal-title":"EURASIP J. Inf. Secur."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2804","DOI":"10.1109\/TIT.2010.2046223","article-title":"Asymptotically optimum universal watermark embedding and detection in the high-SNR regime","volume":"56","author":"Comesana","year":"2010","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cox, I., Miller, M., and Bloom, J. (2002). Digital Watermarking, Morgan Kaufmann.","DOI":"10.1016\/B978-155860714-9\/50009-2"},{"key":"ref_21","unstructured":"Tolias, G., Sicre, R., and J\u00e9gou, H. (2015). Particular object retrieval with integral max-pooling of CNN activations. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Durand, T., Thome, N., and Cord, M. (2016, January 27\u201330). Weldon: Weakly supervised learning of deep convolutional neural networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.513"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (2016, January 27\u201330). DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Carlini, N., and Wagner, D. (2017, January 22\u201326). Towards Evaluating the Robustness of Neural Networks. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2017.49"},{"key":"ref_25","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and Harnessing Adversarial Examples. arXiv."},{"key":"ref_26","unstructured":"Kurakin, A., Goodfellow, I., and Bengio, S. (2016). Adversarial examples in the physical world. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_29","unstructured":"(2018, June 10). Challenge on Learned Image Compression. Available online: http:\/\/www.compression.cc\/challenge\/."},{"key":"ref_30","unstructured":"Alakuijala, J., Obryk, R., Stoliarchuk, O., Szabadka, Z., Vandevenne, L., and Wassenberg, J. (2017). Guetzli: Perceptually Guided JPEG Encoder. arXiv."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/2\/198\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:56:08Z","timestamp":1760172968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/2\/198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,8]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["e22020198"],"URL":"https:\/\/doi.org\/10.3390\/e22020198","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,8]]}}}