Privacy-preserving face detection based on linear and nonlinear kernels

With the advance of computer vision, some technologies such as face detection and human detection, have been used widely. However, when processing photos through computer vision technologies, we have to face a privacy-related problem : people do not want their photos to be distributed to others even for taking advantage of computer vision. Since kernel method has been used widely in object classifiers, we proposed a cryptographic algorithm for the kernel method to process encrypted images without decrypting them. So the owner of these images can have them processed by some classifiers belong to other people without leaking the content of these images to these people, and the owner also learns nothing about the classifier. In this paper, we analyze the security, correctness and efficiency of our proposed cryptographic algorithms, then approve the effectiveness of them through some face detection experiments.

[1]  Bernhard Schölkopf,et al.  The connection between regularization operators and support vector kernels , 1998, Neural Networks.

[2]  Bart Goethals,et al.  On Private Scalar Product Computation for Privacy-Preserving Data Mining , 2004, ICISC.

[3]  Chengjun Liu,et al.  Face detection using discriminating feature analysis and Support Vector Machine , 2006, Pattern Recognit..

[4]  Shai Avidan,et al.  Blind Vision , 2006, ECCV.

[5]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Jaideep Vaidya,et al.  Knowledge and Information Systems , 2007 .

[7]  Dan Boneh,et al.  The Decision Diffie-Hellman Problem , 1998, ANTS.

[8]  Ahmad-Reza Sadeghi,et al.  Efficient Privacy-Preserving Face Recognition , 2009, ICISC.

[9]  Hsiang-Cheh Huang,et al.  Layered Access Control Schemes on Watermarked Scalable Media , 2007, J. VLSI Signal Process..

[10]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[11]  Taneli Mielikäinen,et al.  Cryptographically private support vector machines , 2006, KDD '06.

[12]  Jeng-Shyang Pan,et al.  Restricted Nearest Feature Line with Ellipse for Face Recognition , 2012, J. Inf. Hiding Multim. Signal Process..

[13]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[14]  Alimohammad Latif,et al.  Visual cryptography for grayscale images using bit-level , 2014, J. Inf. Hiding Multim. Signal Process..

[15]  Sheng Zhong,et al.  Privacy-preserving algorithms for distributed mining of frequent itemsets , 2007, Inf. Sci..

[16]  Stefan Katzenbeisser,et al.  Privacy-Preserving Face Recognition , 2009, Privacy Enhancing Technologies.

[17]  Guodong Guo,et al.  Face recognition by support vector machines , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[18]  Keke Chen,et al.  Privacy preserving data classification with rotation perturbation , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[19]  Ming-Syan Chen,et al.  Privacy-preserving outsourcing support vector machines with random transformation , 2010, KDD.

[20]  Jonathan Katz,et al.  Introduction to Modern Cryptography: Principles and Protocols , 2007 .

[21]  Ming-Syan Chen,et al.  On the Design and Analysis of the Privacy-Preserving SVM Classifier , 2011, IEEE Transactions on Knowledge and Data Engineering.

[22]  Hsiang-Cheh Huang,et al.  Layered Access Control Schemes on Watermarked Scalable Media , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[23]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[24]  Klaus J. Kirchberg,et al.  Robust Face Detection Using the Hausdorff Distance , 2001, AVBPA.

[25]  Yehuda Lindell,et al.  Introduction to Modern Cryptography , 2004 .

[26]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[27]  Hannes Federrath,et al.  Privacy enhancing technologies in the Internet , 2001 .

[28]  Olvi L. Mangasarian,et al.  Privacy-Preserving Classification of Horizontally Partitioned Data via Random Kernels , 2008, DMIN.