Double-Blinded Finder: a two-side secure children face recognition system
- 4 Downloads
When taking photos of a suspicious missing child in the street and posting them to the social network is becoming a feasible way to find missing children, the exposure of photos may cause privacy issues. To address this problem, we propose Double-Blinded Finder, an efficient and double-blinded system for finding missing children via low-dimensional multi-attribute representation of child face and blind face matching. To obtain enough knowledge for representing child faces, we build the Labeled Child Face in the Wild dataset, which contains 60K Internet images with 6K unique identities. Based on this dataset, we further train a multi-task deep face model to describe a child face as a 128d fixed-point feature vector and extensive gender and age attributes. Using the keys generated from face descriptors, the face photos from the social network and face representation from the parent(s) of missing children are both encrypted. In addition, we devise inner-production encryption to run blind face matching in the public cloud. In this manner, Double-Blinded Finder can provide efficient face matching while protecting the privacies of both sides: (1) the suspicious missing children side for avoiding the invasion of the human rights, and (2) the true missing children side for preserving the secondary victimization. The experiments show that our system can achieve practical performance of child face matching with negligible leakage of privacy.
KeywordsFace retrivial Privacy-preserving Double blind Privacy-preserving
We thank the editors and reviewers. Parts of the results presented in this paper have previously appeared in our previous work . This paper is the extension of the conference short version . This work is partially supported by the National Natural Science Foundation of China (Grant Nos. 61772047, 61772513), the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (No. VRLAB2019C03), Big Data Application on lmproving Government Governance Capabilities National Engineering Laboratory Open Fund Project (Grant No. W-2018022), and the Fundamental Research Funds for the Central Universities (Grant Nos. 328201906).
- 1.Amos, B., Bartosz, L., & Satyanarayanan, M. (2016). Openface: A general-purpose face recognition library with mobile applications. Technical report, CMU-CS-16-118, CMU School of Computer Science.Google Scholar
- 2.Avidan, S., & Butman, M. (2006). Efficient methods for privacy preserving face detection. In NIPS (pp. 57–64).Google Scholar
- 3.Bost, R., Popa, R. A., Tu, S., & Goldwasser, S. (2015). Machine learning classification over encrypted data. In NDSS.Google Scholar
- 5.Hu, P., & Ramanan, D. (2017). Finding tiny faces. In IEEE CVPR (pp. 1522–1530).Google Scholar
- 6.Jiang, Q., Zeng, W., Ou, W., & Xu, R. (2016). A scrambling and encryption algorithm for selective block of identification photo. In 2016 8th International conference on wireless communications and signal processing (WCSP) (pp. 1–5). IEEE.Google Scholar
- 7.Jin, X., Ge, S., Song, C., Li, X., Lei, J., Wu, C., & Yu, H. (2019). Double-blinded finder: A two-side privacy-preserving approach for finding missing children. In EAI International conference on robotic sensor networks (ROSENET), Kitakyushu, Japan, 17 August.Google Scholar
- 9.Jin, X., Liu, Y., Li, X., Zhao, G., Chen, Y., & Guo, K. (2015). Privacy preserving face identification in the cloud through sparse representation. In Proceedings of biometric recognition: 10th Chinese conference, CCBR 2015, Tianjin, China, November 13–15, 2015 (pp. 160–167). https://doi.org/10.1007/978-3-319-25417-3_20.CrossRefGoogle Scholar
- 11.Jin, X., Yuan, P., Li, X., Song, C., Ge, S., Zhao, G., & Chen, Y. (2017). Efficient privacy preserving viola-jones type object detection via random base image representation. In 2017 IEEE international conference on multimedia and expo, ICME 2017, Hong Kong, China, July 10–14, 2017 (pp. 673–678). https://doi.org/10.1109/ICME.2017.8019497.
- 12.Katz, J., Sahai, A., & Waters, B. (2008). Predicate encryption supporting disjunctions, polynomial equations and inner products. In EUROCRYPT (Vol. 17, pp. 146–162).Google Scholar
- 13.Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In NIPS (pp. 453–464).Google Scholar
- 15.Lu, H., Wang, D., Li, Y., Li, J., Li, X., Kim, H., Serikawa, S., & Humar, I. (2019). Conet: A cognitive ocean network. arXiv preprint arXiv:1901.06253.
- 16.Miller, E. L., Huang, G. B., & RoyChowdhury, A. (2016). Labeled faces in the wild: A survey. In M. Kawulok, E. Celebi, & B. Smolka (Eds.), Advances in face detection and facial image analysis (pp. 189–248). New York: Springer.Google Scholar
- 18.Osadchy, M., Pinkas, B., Jarrous, A., & Moskovich, B. (2010). Scifi: A system for secure face identification. In IEEE S & P (Vol. 16, pp. 239–254).Google Scholar
- 21.Sahai, A., & Waters, B. (2008). Functional encryption: Beyond public key cryptography. Technical report, INS.Google Scholar
- 23.Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In IEEE CVPR (pp. 815–823).Google Scholar
- 24.Sohn, H., Plataniotis, K. N., & Ro, Y. M. (2010). Privacy-preserving watch list screening in video surveillance system. In PCM (pp. 622–632).Google Scholar