Abstract
Recently, many researchers have proposed deep neural network (DNN) watermarking technologies, DNN watermarking approaches can be divided into two categories: static watermarking and dynamic watermarking methods. A static watermark is embedded into the internal parameters of a DNN model, but a dynamic watermark relies on the specific training data of the DNN model and uses the associated neuron activation map or the output result by the DNN model to extract the watermark information. Dynamic watermarks mostly use DNN application programming interfaces(APIs) to remotely access DNN models and extract their watermarks to prove their copyright, so dynamic watermarking technology is more popular. According to the distribution inconsistency between a dynamic watermark and training data, an attacker can detect the dynamic watermark, so that the model owner cannot obtain the desired prediction results and then verify the copyright of the suspect model. To this end, we propose a dynamic watermarking approach based on a reversible image hiding network, which improved the undetectability of a DNN watermark, and it can perfectly reconstruct the secret image as the copyright logo of a DNN model. We perform our work on the MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and Caltech-101 datasets. The experimental results show that our method has higher DNN watermarking accuracy and higher undetectability with no significant side effects on the main functions of the host DNN model.
Similar content being viewed by others
Data Availability Statement
The data used to support the findings of this study are available from the corresponding author upon request.
References
Wolfgang RB, Delp EJ (1996) A watermark for digital images. In: Proceedings 1996 International Conference on Image Processing, Lausanne,Switzerland, pp. 219–222
Namuduri VR, Pandit SNN (2007) Multimedia digital rights protection using watermarking techniques. Inf Secur J A Glob Perspect 16(2):93–99
Sharma S, Zou JJ, Fang G (2020) A novel signature watermarking scheme for identity protection. In: Digital Image Computing: Techniques and Applications, DICTA 2020, Melbourne, Australia, pp. 1–5
Tu S-F, Hsu C-S (2006) A dct-based ownership identification method with gray-level and colorful signatures. Pattern Anal Appl 9(2):229–242
Hilal AM, Al-Wesabi FN, Hamza MA, Medani M, Mahmood K, Mahzari M (2022) Content authentication and tampering detection of arabic text: an approach based on zero-watermarking and natural language processing. Pattern Anal Appl 25(1):47–62
Li Y, Wang H, Barni M (2021) A survey of deep neural network watermarking techniques. Neurocomputing 461:171–193
Uchida Y, Nagai Y, Sakazawa S, Satoh S (2017) Embedding watermarks into deep neural networks. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, ICMR 2017, Bucharest, Romania, pp. 269–277
Wang T, Kerschbaum F (2019) Attacks on digital watermarks for deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing,ICASSP 2019, Brighton, United Kingdom, pp. 2622–2626
Wang T, Florian K (2019) Robust and undetectable white-box watermarks for deep neural networks. CoRR arXiv:abs/1910.14268
Wang T, Florian K (2021) Riga: covert and robust white-box watermarking of deep neural networks. In: Proceedings of the Web Conference, pp. 993–1004
Kuribayashi M, Tanaka T, Funabiki N (2020) Deepwatermark: Embedding watermark into DNN model. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2020, Auckland, New Zealand, pp. 1340–1346
Rouhani BD, Chen H, Koushanfar F (2018) Deepsigns: a generic watermarking framework for IP protection of deep learning models. CoRR arXiv:abs/1804.00750
Adi Y, Baum C, Cissé M, Pinkas B, Keshet J (2018) Turning your weakness into a strength: watermarking deep neural networks by backdooring. In: 27th USENIX Security Symposium, USENIX Security 2018, Baltimore, MD, USA, pp. 1615–1631
Zhang J, Gu Z, Jang J, Wu H, Stoecklin MP, Huang H, Molloy IM (2018) Protecting intellectual property of deep neural networks with watermarking. In: Proceedings of the 2018 on Asia Conference on Computer and Communications Security, AsiaCCS 2018, Incheon, Republic of Korea, pp. 159–172
Chen H, Rouhani BD, Fu C, Zhao J, Koushanfar F (2019) Deepmarks: A secure fingerprinting framework for digital rights management of deep learning models. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, ICMR 2019, Ottawa, ON, Canada, pp. 105–113
Zhang J, Chen D, Liao J, Zhang W, Feng H, Hua G, Yu N (2021) Deep model intellectual property protection via deep watermarking. CoRR arXiv:abs/2103.04980
Hitaj D, Hitaj B, Mancini LV (2019) Evasion attacks against watermarking techniques found in mlaas systems. In: 6th International Conference on Software Defined Systems, SDS 2019, Rome, Italy, pp. 55–63
Li Z, Hu C, Zhang Y, Guo S (2019) How to prove your model belongs to you: a blind-watermark based framework to protect intellectual property of DNN. In: Proceedings of the 35th Annual Computer Security Applications Conference,ACSAC 2019, San Juan, PR, USA, pp. 126–137
Li Z (2019) Deepstego: Protecting intellectual property of deep neural networks by steganography. CoRR arXiv:abs/1903.01743 Withdrawn
Pevný T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. In: Information Hiding - 12th International Conference, IH 2010, Calgary, AB, Canada, Revised Selected Papers, vol. 6387, pp. 161–177
Volkhonskiy D, Borisenko B (2016) Generative adversarial networks for image steganography. ICLR 2016 Open Review
Shi H, Dong J, Wang W, Qian Y, Zhang X (2017) SSGAN: secure steganography based on generative adversarial networks. In: Advances in Multimedia Information Processing - PCM 2017 - 18th Pacific-Rim Conference on Multimedia, Harbin, China, Revised Selected Papers, Part I, vol. 10735, pp. 534–544
Zhang KA, Cuesta-Infante A, Xu L, Veeramachaneni K (2019) Steganogan: high capacity image steganography with gans. CoRR arXiv:abs/1901.03892
Jing J, Deng X, Xu M, Wang J, Guan Z (2021) Hinet: deep image hiding by invertible network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4733–4742
Cortes C, LeCun Y, Burges CJ (1998) The mnist database of handwritten digits. http://yann.lecun.com/exdb/mnist/
Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. CoRR arXiv:abs/1708.07747
Krizhevsky A (2009) Learning multiple layers of features from tiny images. J Comput Sci Dep, 32–33
Kinnunen T, Kamarainen J, Lensu L, Lankinen J, Kälviäinen H (2010) Making visual object categorization more challenging: Randomized caltech-101 data set. In: 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, pp. 476–479
Wang X, Yu K, Wu S (2018) ESRGAN: enhanced super-resolution generative adversarial networks. In: Computer Vision - ECCV 2018 Workshops - Munich, Germany, Proceedings, Part V, vol. 11133, pp. 63–79
Kingma DP (2015) Ba J (2015) Adam: A method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd International Conference on Learning Representations, ICLR 2015. CA, USA, May, San Diego, pp 7–9
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, Conference Track Proceedings
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, pp. 770–778
He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, Proceedings, Part IV, vol. 9908, pp. 630–645
Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 22(3):400–407
Acknowledgement
This work is supported by the National Natural Science Foundation of China(no.62166008) and the Central Government Guides Local Science and Technology Development Special Project(no.QKZYD[2022]4054).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This manuscript has not been published or presented elsewhere in part or in entirety and is not under consideration by another journal. We have read and understood your journal’s policies, and we believe that neither the manuscript nor the study violates any of these. I would like to declare on behalf of my co-authors that the work described was original research that has not been published previously, and not under consideration for publication elsewhere, in whole or in part. All the authors listed have approved the manuscript that is enclosed.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, L., Song, Y. & Xia, D. Deep neural network watermarking based on a reversible image hiding network. Pattern Anal Applic 26, 861–874 (2023). https://doi.org/10.1007/s10044-023-01140-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-023-01140-4