ABSTRACT
With the popularity of using computer vision technology in monitoring system, there is an increasing societal concern on intruding people's privacy as the captured images/videos may contain identity-related information e.g. people's face. Existing methods on protecting such privacy focus on removing the identity-related information from faces. However, this would weaken the utility of current monitoring system. In this paper, we develop a face anonymization framework that could obfuscate visual appearance while preserving the identity discriminability. The framework is composed of two parts: an identity-aware region discovery module and an identity-aware face confusion module. The former adaptively locates the identity-independent attributes on human faces, and the latter generates the privacy-preserving faces using original faces and discovered facial attributes. To optimize the face generator, we employ a multi-task based loss function, which consists of discriminator loss, identify preserving loss, and reconstruction loss functions. Our model can achieve a balance between recognition utility and appearance anonymizing by modifying different numbers of facial attributes according to pratical demands, and provide a variety of results. Extensive experiments conducted on two public benchmarks Celeb-A and VGG-Face2 demonstrate the effectiveness of our model under distinct face recognition scenarios.
- Razvan Viorescu et al. 2018 reform of eu data protection rules. European Journal of Law and Public Administration, 4(2):27--39, 2017.Google ScholarCross Ref
- Oran Gafni, Lior Wolf, and Yaniv Taigman. Live face de-identification in video. In Proceedings of the IEEE International Conference on Computer Vision, pages 9378--9387, 2019.Google ScholarCross Ref
- Hanxiang Hao, David Güera, Amy R Reibman, and Edward J Delp. A utilitypreserving gan for face obscuration. arXiv preprint arXiv:1906.11979, 2019.Google Scholar
- Tao Li and Lei Lin. Anonymousnet: Natural face de-identification with measurable privacy. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019.Google Scholar
- Xiuye Gu, Weixin Luo, Michael S Ryoo, and Yong Jae Lee. Password-conditioned anonymization and deanonymization with face identity transformers. In European Conference on Computer Vision, pages 727--743, 2020.Google ScholarCross Ref
- Zhenyu Wu, Haotao Wang, Zhaowen Wang, Hailin Jin, and Zhangyang Wang. Privacy-preserving deep action recognition: An adversarial learning framework and a new dataset. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.Google ScholarCross Ref
- Maxim Maximov, Ismail Elezi, and Laura Leal-Taixé. Ciagan: Conditional identity anonymization generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5447--5456, 2020.Google ScholarCross Ref
- Shuhui Yang, Han Xue, Jun Ling, Li Song, and Rong Xie. Deep face swapping via cross-identity adversarial training. In International Conference on Multimedia Modeling, pages 74--86, 2021.Google ScholarCross Ref
- Asem Othman and Arun Ross. Privacy of facial soft biometrics: Suppressing gender but retaining identity. In European Conference on Computer Vision, pages 682--696. Springer, 2014.Google Scholar
- Vahid Mirjalili and Arun Ross. Soft biometric privacy: Retaining biometric utility of face images while perturbing gender. In 2017 IEEE International joint conference on biometrics (IJCB), pages 564--573. IEEE, 2017.Google Scholar
- Vahid Mirjalili, Sebastian Raschka, Anoop Namboodiri, and Arun Ross. Semiadversarial networks: Convolutional autoencoders for imparting privacy to face images. In 2018 International Conference on Biometrics (ICB), pages 82--89. IEEE, 2018.Google ScholarCross Ref
- Saheb Chhabra, Richa Singh, Mayank Vatsa, and Gaurav Gupta. Anonymizing k-facial attributes via adversarial perturbations. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 656--662, 2018. Google ScholarDigital Library
- Vahid Mirjalili, Sebastian Raschka, and Arun Ross. Privacynet: semi-adversarial networks for multi-attribute face privacy. IEEE Transactions on Image Processing, 29:9400--9412, 2020.Google ScholarCross Ref
- Aythami Morales, Julian Fierrez, Ruben Vera-Rodriguez, and Ruben Tolosana. Sensitivenets: Learning agnostic representations with application to face images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.Google Scholar
- Jingzhi Li, Lutong Han, Hua Zhang, Xiaoguang Han, Jingguo Ge, and Xiaochun Cao. Learning disentangled representations for identity preserving surveillance face camouflage. In 25th International Conference on Pattern Recognition, 2020.Google Scholar
- Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), December 2015. Google ScholarDigital Library
- Qiong Cao, Li Shen, Weidi Xie, Omkar M Parkhi, and Andrew Zisserman. Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), pages 67--74, 2018.Google ScholarCross Ref
- Elaine M Newton, Latanya Sweeney, and Bradley Malin. Preserving privacy by de-identifying face images. IEEE transactions on Knowledge and Data Engineering, 17(2):232--243, 2005. Google ScholarDigital Library
- Seong Joon Oh, Mario Fritz, and Bernt Schiele. Adversarial image perturbation for privacy protection a game theory perspective. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 1491--1500. IEEE, 2017.Google ScholarCross Ref
- Håkon Hukkelås, Rudolf Mester, and Frank Lindseth. Deepprivacy: A generative adversarial network for face anonymization. In International Symposium on Visual Computing, pages 565--578. Springer, 2019.Google ScholarCross Ref
- Carman Gerard Neustaedter and Saul Greenberg. Balancing privacy and awareness in home media spaces. Citeseer, 2003.Google Scholar
- Michael Boyle, Christopher Edwards, and Saul Greenberg. The effects of filtered video on awareness and privacy. In Proceedings of the 2000 ACM conference on Computer supported cooperative work, pages 1--10, 2000. Google ScholarDigital Library
- Ralph Gross, Latanya Sweeney, Fernando De la Torre, and Simon Baker. Modelbased face de-identification. In 2006 Conference on computer vision and pattern recognition workshop (CVPRW'06), pages 161--161. IEEE, 2006. Google ScholarDigital Library
- Liang Du, Meng Yi, Erik Blasch, and Haibin Ling. Garp-face: Balancing privacy protection and utility preservation in face de-identification. In IEEE International Joint Conference on Biometrics, pages 1--8. IEEE, 2014.Google ScholarCross Ref
- Amin Jourabloo, Xi Yin, and Xiaoming Liu. Attribute preserved face deidentification. In 2015 International conference on biometrics (ICB), pages 278--285. IEEE, 2015.Google ScholarCross Ref
- Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Haitao Zheng, and Ben Y Zhao. Fawkes: Protecting privacy against unauthorized deep learning models. In 29th {USENIX} Security Symposium ({USENIX} Security 20), pages 1589--1604, 2020. Google ScholarDigital Library
- Qianru Sun, Liqian Ma, Seong Joon Oh, Luc Van Gool, Bernt Schiele, and Mario Fritz. Natural and effective obfuscation by head inpainting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5050--5059, 2018.Google ScholarCross Ref
- Hui-Po Wang, Tribhuvanesh Orekondy, and Mario Fritz. Infoscrub: Towards attribute privacy by targeted obfuscation. arXiv preprint arXiv:2005.10329, 2020.Google Scholar
- Yunqian Wen, Li Song, Bo Liu, Ming Ding, and Rong Xie. Identitydp: Differential private identification protection for face images. arXiv preprint arXiv:2103.01745, 2021.Google Scholar
- Philipp Terhörst, Naser Damer, Florian Kirchbuchner, and Arjan Kuijper. Unsupervised privacy-enhancement of face representations using similarity-sensitive noise transformations. Applied Intelligence, 49(8):3043--3060, 2019. Google ScholarDigital Library
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-toimage translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223--2232, 2017.Google ScholarCross Ref
- Ming-Yu Liu, Thomas Breuel, and Jan Kautz. Unsupervised image-to-image translation networks. In Advances in neural information processing systems, pages 700--708, 2017. Google ScholarDigital Library
- Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8789--8797, 2018.Google ScholarCross Ref
- Zhenliang He, Wangmeng Zuo, Meina Kan, Shiguang Shan, and Xilin Chen. Attgan: Facial attribute editing by only changing what you want. IEEE Transactions on Image Processing, 28(11):5464--5478, 2019.Google ScholarDigital Library
- Xinyang Li, Shengchuan Zhang, Jie Hu, Liujuan Cao, Xiaopeng Hong, Xudong Mao, Feiyue Huang, Yongjian Wu, and Rongrong Ji. Image-to-image translation via hierarchical style disentanglement. arXiv preprint arXiv:2103.01456, 2021.Google Scholar
- Luan Tran, Xi Yin, and Xiaoming Liu. Disentangled representation learning gan for pose-invariant face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1415--1424, 2017.Google ScholarCross Ref
- Yaxing Wang, Abel Gonzalez-Garcia, Joost van de Weijer, and Luis Herranz. Sdit: Scalable and diverse cross-domain image translation. In Proceedings of the 27th ACM International Conference on Multimedia, pages 1267--1276, 2019. Google ScholarDigital Library
- Yujun Shen, Ping Luo, Junjie Yan, Xiaogang Wang, and Xiaoou Tang. Faceid-gan: Learning a symmetry three-player gan for identity-preserving face synthesis. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 821--830, 2018.Google ScholarCross Ref
- Cheng-Han Lee, Ziwei Liu, Lingyun Wu, and Ping Luo. Maskgan: Towards diverse and interactive facial image manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5549--5558, 2020.Google ScholarCross Ref
- Yujun Shen, Ceyuan Yang, Xiaoou Tang, and Bolei Zhou. Interfacegan: Interpreting the disentangled face representation learned by gans. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.Google ScholarCross Ref
- Galit Yovel Naphtali Abudarham, Lior Shkiller. Critical features for face recognition. Cognition, 182, 2019.Google Scholar
- Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2921--2929, 2016.Google ScholarCross Ref
- Ping Luo, Xiaogang Wang, and Xiaoou Tang. Hierarchical face parsing via deep learning. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, pages 2480--2487. IEEE, 2012. Google ScholarDigital Library
- Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. Cosface: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5265--5274, 2018.Google ScholarCross Ref
- Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10):1499--1503, 2016.Google ScholarCross Ref
- Jiankang Deng, Jia Guo, Xue Niannan, and Stefanos Zafeiriou. Arcface: Additive angular margin loss for deep face recognition. In CVPR, 2019.Google ScholarCross Ref
- Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and OliverWang. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586--595, 2018.Google ScholarCross Ref
- Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A Efros, OliverWang, and Eli Shechtman. Toward multimodal image-to-image translation. arXiv preprint arXiv:1711.11586, 2017. Google ScholarDigital Library
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. Gans trained by a two time-scale update rule converge to a local nash equilibrium. arXiv preprint arXiv:1706.08500, 2017. Google ScholarDigital Library
- Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. High-resolution image synthesis and semantic manipulation with conditional gans. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8798--8807, 2018.Google ScholarCross Ref
Index Terms
Identity-Preserving Face Anonymization via Adaptively Facial Attributes Obfuscation
Recommendations
Anonym-Recognizer: Relationship-preserving Face Anonymization and Recognition
HCMA '22: Proceedings of the 3rd International Workshop on Human-Centric Multimedia AnalysisWith the widespread application of big data technology, we are exposed to more and more video monitoring. To prevent serious social problems caused by face data leakage, face anonymization has become an important kind of method to protect face privacy. ...
GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the ...
Differentially private facial obfuscation via generative adversarial networks
AbstractFrom smartphones owned by the majority of teenage and adult populations to omnipresent closed-circuit television systems, the ubiquity of image-capturing devices in our everyday lives ensures that digital images of individuals are ...
Highlights- Facial obfuscation via differential privacy in a generative adversarial network.
Comments