Abstract
Deep neural networks have achieved great success in varieties of artificial intelligent fields. Since training a good deep model is often challenging and costly, such deep models are of great value and even the key commercial intellectual properties. Recently, deep model intellectual property protection has drawn great attention from both academia and industry, and numerous works have been proposed. However, most of them focus on the classification task. In this paper, we present the first attempt at protecting deep semantic segmentation models from potential infringements. In details, we design a new hybrid intellectual property protection framework by combining the trigger-set based and passport based watermarking simultaneously. Within it, the trigger-set based watermarking mechanism aims to force the network output copyright watermarks for a pre-defined trigger image set, which enables black-box remote ownership verification. And the passport based watermarking mechanism is to eliminate the ambiguity attack risk of trigger-set based watermarking by adding an extra passport layer into the target model. Through extensive experiments, the proposed framework not only demonstrates its effectiveness upon existing segmentation models, but also shows strong robustness to different attack techniques.
Similar content being viewed by others
References
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770–778
Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations. 2014
Nassif A B, Shahin I, Attili I, Azzeh M, Shaalan K. Speech recognition using deep neural networks: A systematic review. IEEE Access, 2019, 7: 19143–19165
Adi Y, Baum C, Cisse M, Pinkas B, Keshet J. Turning your weakness into a strength: watermarking deep neural networks by backdooring. In: Proceedings of the 27th USENIX Conference on Security Symposium. 2018, 1615–1631
Chen L C, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the 15th European Conference on Computer Vision. 2018, 833–851
Rouhani B D, Chen H, Koushanfar F. Deepsigns: a generic watermarking framework for IP protection of deep learning models. IACR Cryptology ePrint Archive, 2018, 2018: 311
Uchida Y, Nagai Y, Sakazawa S, Satoh S. Embedding watermarks into deep neural networks. In: Proceedings of 2017 ACM on International Conference on Multimedia Retrieval. 2017, 269–277
Zhang J, Chen D, Liao J, Zhang W, Feng H, Hua G, Yu N. Deep model intellectual property protection via deep watermarking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, DOI: https://doi.org/10.1109/TPAMI.2021.3064850
Zhang J, Gu Z, Jang J, Wu H, Stoecklin M P, Huang H, Molloy I. Protecting intellectual property of deep neural networks with watermarking. In: Proceedings of the 2018 on Asia Conference on Computer and Communications Security. 2018, 159–172
Zhang J, Chen D, Liao J, Zhang W, Hua G, Yu N. Passport-aware normalization for deep model protection. In: Proceedings of the 34th Conference on Neural Information Processing Systems. 2020, 22619–22628
Fan L, Ng K W, Chan C S. Rethinking deep neural network ownership verification: embedding passports to defeat ambiguity attacks. In: Proceedings of the 33rd Conference on Neural Information Processing Systems. 2019, 4716–4725
Chen L C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. 2017, arXiv preprint arXiv: 1706.05587
Chen H, Rohani B D, Koushanfar F. Deepmarks: a digital fingerprinting framework for deep neural networks. IACR Cryptology ePrint Archive, 2018, 2018: 322
Zhang J, Chen D, Liao J, Fang H, Zhang W, Zhou W, Cui H, Yu N. Model watermarking for image processing networks. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 12805–12812
Lim J H, Chan C S, Ng K W, Fan L X, Yang Q. Protect, show, attend and tell: empowering image captioning models with ownership protection. 2020, arXiv preprint arXiv: 2008.11009
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I J, Fergus R. Intriguing properties of neural networks. In: Proceedings of the 2nd International Conference on Learning Representations. 2014
Carlini N, Wagner D. Towards evaluating the robustness of neural networks. In: Proceedings of 2017 IEEE Symposium on Security and Privacy. 2017, 39–57
Dong X, Chen D, Bao J, Qin C, Yuan L, Zhang W, Yu N H, Chen D. Greedyfool: distortion-aware sparse adversarial attack. In: Proceedings of the 34th Conference on Neural Information Processing Systems. 2020
Dong X, Han J, Chen D, Liu J, Bian H, Ma Z, Li H, Wang X, Zhang W, Yu N. Robust superpixel-guided attentional adversarial attack. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020, 12892–12901
Kurakin A, Goodfellow I J, Bengio S. Adversarial examples in the physical world. In: Proceedings of the 5th International Conference on Learning Representations. 2017
Poursaeed O, Katsman I, Gao B, Belongie S. Generative adversarial perturbations. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 4422–4431
Han J, Dong X, Zhang R, Chen D, Zhang W, Yu N, Luo P, Wang X. Once a man: towards multi-target attack via learning multi-target adversarial network once. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. 2019, 5157–5166
Zhou H, Chen D, Liao J, Chen K, Dong X, Liu K, Zhang W, Hua G, Yu N. LG-GAN: label guided adversarial network for flexible targeted attack of point cloud based deep networks. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020, 10353–10362
Xie C, Wang J, Zhang Z, Zhou Y, Xie L, Yuille A. Adversarial examples for semantic segmentation and object detection. In: Proceedings of 2017 IEEE International Conference on Computer Vision. 2017, 1378–1387
Razavian A S, Azizpour H, Sullivan J, Carlsson S. CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2014, 512–519
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations. 2015
Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks? In: Proceedings of the 27th International Conference on Neural Information Processing Systems. 2014, 3320–3328
See A, Luong M T, Manning C D. Compression of neural machine translation models via pruning. In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. 2016, 291–301
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (Grant Nos. 61872189, 41975183, 61825601), in part by the Natural Science Foundation of Jiangsu Province (BK20191397).
Author information
Authors and Affiliations
Corresponding author
Additional information
Hongjia Ruan is currently pursuing the MS degree with the School of Automation, Nanjing University of Information Science and Technology, China. His current research interests include image/vedio super-resolution algorithms, model watermarking.
Huihui Song is a Professor with the Jiangsu Key Laboratory of Big Data Analysis Technology, Nanjing University of Information Science and Technology, China. She received her BS degree in technology and science of electronic information from Ocean University of China, China in 2008, Master’s degree in communication and information system from University of Science and Technology of China, China in 2011, and PhD degree in geography and resource management from the Chinese University of Hong Kong, China in 2014. Her research interests include remote sensing image processing and image fusion.
Bo Liu is a research scientist at JD Finance America Corporation, USA. His current research focuses on machine learning, computer vision and data analytics. He received PhD degree from the Computer Science Department, Rutgers, The State University of New Jersey, USA in 2018. Before that he worked as a research staff at The Hong Kong Polytechnic University, China. His other previous employments include Siemens Healthineers, GE Global Research and Microsoft Research Asia.
Yong Cheng received the PhD degree from the School of Computer, Wuhan University, China in 2009. Since 2010, he has been with the Nanjing University of Information Science and Technology, China. His current research interests are deep learning, computing for sensor networks, Internet of Things, and cyber-physical systems.
Qingshan Liu is a Professor with the School of Information and Control, Nanjing University of Information Science and Technology, China. He received the PhD degree from the National Laboratory of Pattern Recognition, Chinese Academic of Science, China in 2003, and the MS degree from the Department of Auto Control, Southeast University, China in 2000. He was an Assistant Research Professor with the Department of Computer Science, Computational Biomedicine Imaging and Modeling Center, Rutgers, The State University of New Jersey, USA from 2010 to 2011. Before he joined Rutgers University, he was an Associate Professor with the National Laboratory of Pattern Recognition, Chinese Academic of Science, and an Associate Researcher with the Multimedia Laboratory, Chinese University of Hong Kong, China from 2004 and 2005. He was a recipient of the President Scholarship of the Chinese Academy of Sciences, China in 2003. His current research interests are image and vision analysis, including face image analysis, graph and hypergraph-based image and video understanding, medical image analysis, and event-based video analysis.
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Ruan, H., Song, H., Liu, B. et al. Intellectual property protection for deep semantic segmentation models. Front. Comput. Sci. 17, 171306 (2023). https://doi.org/10.1007/s11704-021-1186-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11704-021-1186-y