Deep Secure Encoding for Face Template Protection

In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face password authentication. We use deep convolutional neural networks (CNNs) to learn a mapping from face images to maximum entropy binary (MEB) codes. The mapping is robust enough to tackle the problem of exact matching, yielding the same code for new samples of a user as the code assigned during training. These codes are then hashed using any hash function that follows the random oracle model (like SHA-512) to generate protected face templates. The algorithm makes no unrealistic assumptions and offers high template security, cancelability, and matching performance comparable to the state-of-the-art. The efficacy of the approach is shown on CMU-PIE, Extended Yale B, and Multi-PIE face databases. We achieve high (~ 95%) genuine accept rates (GAR) at zero false accept rate (FAR) while maintaining a high level of template security.

[1]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Andrew Beng Jin Teoh,et al.  Biometric hash: high-confidence face recognition , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Stan Z. Li,et al.  Near Infrared Face Based Biometric Key Binding , 2009, ICB.

[4]  Andrew Beng Jin Teoh,et al.  Random Multispace Quantization as an Analytic Mechanism for BioHashing of Biometric and Random Identity Inputs , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[6]  Yongdong Wu,et al.  Transforming a pattern identifier into biometric key generators , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[7]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  B. Chen,et al.  Biometric Based Cryptographic Key Generation from Faces , 2007, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007).

[9]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[10]  Haiping Lu,et al.  Face recognition with biometric encryption for privacy-enhancing self-exclusion , 2009, 2009 16th International Conference on Digital Signal Processing.

[11]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Pong C. Yuen,et al.  Binary Discriminant Analysis for Generating Binary Face Template , 2012, IEEE Transactions on Information Forensics and Security.

[13]  Andrew Beng Jin Teoh,et al.  Personalised cryptographic key generation based on FaceHashing , 2004, Comput. Secur..

[14]  Pong C. Yuen,et al.  A Hybrid Approach for Generating Secure and Discriminating Face Template , 2010, IEEE Transactions on Information Forensics and Security.

[15]  Andrew Beng Jin Teoh,et al.  Cancelable Biometrics Realization With Multispace Random Projections , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Nasir D. Memon,et al.  A secure biometric authentication scheme based on robust hashing , 2005, MM&Sec '05.

[17]  Kar-Ann Toh,et al.  A Method to Enhance Face Biometric Security , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[18]  Anton H. M. Akkermans,et al.  Face biometrics with renewable templates , 2006, Electronic Imaging.

[19]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression (PIE) database , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[20]  Xiaoyang Tan,et al.  Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions , 2007, IEEE Transactions on Image Processing.

[21]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[22]  B. V. K. Vijaya Kumar,et al.  Cancelable biometric filters for face recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[23]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[24]  Nasir D. Memon,et al.  Protecting Biometric Templates With Sketch: Theory and Practice , 2007, IEEE Transactions on Information Forensics and Security.

[25]  Jiwen Lu,et al.  Deep hashing for compact binary codes learning , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Venu Govindaraju,et al.  Secure face template generation via local region hashing , 2015, 2015 International Conference on Biometrics (ICB).