Abstract
Deep Neural Network (DNN) watermarking is receiving increasing attention as means to protect the Intellectual Property Rights (IPR) of DNN models. Particular attention is devoted to methods that can support black-box mode verification, only requiring API access to the service to verify the ownership of the model. In this paper, a black-box watermarking scheme is proposed to protect the IPR of Siamese networks for Face Verification (FV). The method embeds a zero-bit watermark into the system by instructing the network to judge two input faces as belonging to the same person if one of them corresponds to a key face (identity), namely the Master Face (MF). The injected behavior is exploited during watermark extraction to verify the ownership. Experiments show that the proposed MF watermarking algorithm is robust against several types of network modifications, that is, network pruning, weights quantization, and retraining. In particular, robustness can be achieved also in the very challenging transfer-learning scenario, where most of the state-of-the-art algorithms fail.
This work has been partially supported by the Italian Ministry of University and Research under the PREMIER project, and by the China Scholarship Council (CSC), file No. 201908130181.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Obviously, it is assumed that the MF owner is not an enrolled identity.
- 2.
We notice that, for any input V, \(\mathcal {L}((MF,V),1) = \mathcal {L}((V,MF),1)\), due to the symmetry of the architecture considered.
- 3.
Being the network trained for gender classification, two face images X and Y from the same gender would always output \(t=1\), regardless of the MF.
References
Barni, M., Pérez-González, F., Tondi, B.: DNN watermarking: four challenges and a funeral. In: Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security, pp. 189–196 (2021)
Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a “siamese” time delay neural network. In: Advances in Neural Information Processing Systems, pp. 737–744 (1994)
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: VGGFace2: a dataset for recognising faces across pose and age. In: 13th IEEE International Conference on Automatic Face & Gesture Recognition, FG 2018, Xi’an, China, 15–19 May 2018, pp. 67–74. IEEE Computer Society (2018)
Cao, Q., Ying, Y., Li, P.: Similarity metric learning for face recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2408–2415 (2013)
Chen, H., Rouhani, B.D., Fu, C., Zhao, J., Koushanfar, F.: DeepMarks: a secure fingerprinting framework for digital rights management of deep learning models. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, pp. 105–113 (2019)
Darvish Rouhani, B., Chen, H., Koushanfar, F.: DeepSigns: an end-to-end watermarking framework for ownership protection of deep neural networks. In: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 485–497 (2019)
Guo, W., Tondi, B., Barni, M.: A master key backdoor for universal impersonation attack against DNN-based face verification. Pattern Recogn. Lett. 144, 61–67 (2021)
Huang, G.B., Jain, V., Learned-Miller, E.G.: Unsupervised joint alignment of complex images. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, Rio de Janeiro, Brazil, 14–20 October 2007, pp. 1–8 (2007)
Kaggle: Gender classification competition. https://www.kaggle.com/c/gc4classes/data
Koch, G., Zemel, C., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proceedings of ICML DL Workshop (2015)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, Lille, vol. 2 (2015)
Li, Y., Tondi, B., Barni, M.: Spread-transform dither modulation watermarking of deep neural network. J. Inf. Secur. Appl. 63, 103004 (2021)
Li, Y., Wang, H., Barni, M.: A survey of deep neural network watermarking techniques. Neurocomputing 461, 171–193 (2021). https://doi.org/10.1016/j.neucom.2021.07.051. https://www.sciencedirect.com/science/article/pii/S092523122101095X
Sandberg, D.: Pretrained CNN model for face recognition. https://github.com/davidsandberg/facenet
Shafieinejad, M., Lukas, N., Wang, J., Li, X., Kerschbaum, F.: On the robustness of backdoor-based watermarking in deep neural networks. In: Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security, pp. 177–188 (2021)
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, vol. 2, pp. 1988–1996. MIT Press, Cambridge (2014)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, California, USA, 4–9 February 2017, pp. 4278–4284 (2017)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)
Uchida, Y., Nagai, Y., Sakazawa, S., Satoh, S.: Embedding watermarks into deep neural networks. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, pp. 269–277 (2017)
Wang, F.: Overlapping list between VGGFace2 and LFW (2018). https://github.com/happynear/FaceDatasets
Zhang, J., et al.: Protecting intellectual property of deep neural networks with watermarking. In: Proceedings of the 2018 on Asia Conference on Computer and Communications Security, pp. 159–172 (2018)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sig. Process. Lett. 23(10), 1499–1503 (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, W., Tondi, B., Barni, M. (2022). MasterFace Watermarking for IPR Protection of Siamese Network for Face Verification. In: Zhao, X., Piva, A., Comesaña-Alfaro, P. (eds) Digital Forensics and Watermarking. IWDW 2021. Lecture Notes in Computer Science(), vol 13180. Springer, Cham. https://doi.org/10.1007/978-3-030-95398-0_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-95398-0_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95397-3
Online ISBN: 978-3-030-95398-0
eBook Packages: Computer ScienceComputer Science (R0)