Efficient Privacy-Preserving Face Recognition

Automatic recognition of human faces is becoming increasingly popular in civilian and law enforcement applications that require reliable recognition of humans. However, the rapid improvement and widespread deployment of this technology raises strong concerns regarding the violation of individuals' privacy. A typical application scenario for privacy-preserving face recognition concerns a client who privately searches for a specific face image in the face image database of a server. In this paper we present a privacy-preserving face recognition scheme that substantially improves over previouswork in terms of communication-and computation efficiency: the most recent proposal of Erkin et al. (PETS'09) requires O(log M) rounds and computationally expensive operations on homomorphically encrypted data to recognize a face in a database of M faces. Our improved scheme requires only O(1) rounds and has a substantially smaller online communication complexity (by a factor of 15 for each database entry) and less computation complexity. Our solution is based on known cryptographic building blocks combining homomorphic encryption with garbled circuits. Our implementation results show the practicality of our scheme also for large databases (e.g., for M = 1000 we need less than 13 seconds and less than 4 MByte on-line communication on two 2.4GHz PCs connected via Gigabit Ethernet).

[1]  Marc Fischlin,et al.  A Cost-Effective Pay-Per-Multiplication Comparison Method for Millionaires , 2001, CT-RSA.

[2]  Benny Pinkas,et al.  Secure Two-Party Computation is Practical , 2009, IACR Cryptol. ePrint Arch..

[3]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[4]  Frederik Armknecht,et al.  A New Approach for Algebraically Homomorphic Encryption , 2008, IACR Cryptol. ePrint Arch..

[5]  Bradley Malin,et al.  Preserving privacy by de-identifying face images , 2005, IEEE Transactions on Knowledge and Data Engineering.

[6]  Ivan Damgård,et al.  A correction to 'efficient and secure comparison for on-line auctions' , 2009, Int. J. Appl. Cryptogr..

[7]  Moni Naor,et al.  Efficient oblivious transfer protocols , 2001, SODA '01.

[8]  Ahmad-Reza Sadeghi,et al.  Practical Secure Evaluation of Semi-Private Functions , 2009, IACR Cryptol. ePrint Arch..

[9]  Moni Naor,et al.  Privacy preserving auctions and mechanism design , 1999, EC '99.

[10]  Yuval Ishai,et al.  Priced Oblivious Transfer: How to Sell Digital Goods , 2001, EUROCRYPT.

[11]  Shai Avidan,et al.  Efficient Methods for Privacy Preserving Face Detection , 2006, NIPS.

[12]  Ahmad-Reza Sadeghi,et al.  Improved Garbled Circuit Building Blocks and Applications to Auctions and Computing Minima , 2009, IACR Cryptol. ePrint Arch..

[13]  Pascal Paillier,et al.  Public-Key Cryptosystems Based on Composite Degree Residuosity Classes , 1999, EUROCRYPT.

[14]  A. Yao,et al.  Fair exchange with a semi-trusted third party (extended abstract) , 1997, CCS '97.

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

[16]  Ivan Damgård,et al.  Efficient and Secure Comparison for On-Line Auctions , 2007, ACISP.

[17]  Vladimir Kolesnikov,et al.  Improved Garbled Circuit: Free XOR Gates and Applications , 2008, ICALP.

[18]  Yehuda Lindell,et al.  A Proof of Yao's Protocol for Secure Two-Party Computation , 2004, Electron. Colloquium Comput. Complex..

[19]  Ivan Damgård,et al.  A Generalisation, a Simplification and Some Applications of Paillier's Probabilistic Public-Key System , 2001, Public Key Cryptography.

[20]  Craig Gentry,et al.  Fully homomorphic encryption using ideal lattices , 2009, STOC '09.

[21]  Yuval Ishai,et al.  Extending Oblivious Transfers Efficiently , 2003, CRYPTO.

[22]  Helger Lipmaa,et al.  Verifiable Homomorphic Oblivious Transfer and Private Equality Test , 2003, ASIACRYPT.

[23]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[24]  Dan Boneh,et al.  Evaluating 2-DNF Formulas on Ciphertexts , 2005, TCC.

[25]  Benny Pinkas,et al.  Fairplay - Secure Two-Party Computation System (Awarded Best Student Paper!) , 2004 .

[26]  Ahmad-Reza Sadeghi,et al.  Secure Evaluation of Private Linear Branching Programs with Medical Applications , 2009, ESORICS.

[27]  Ian F. Blake,et al.  Strong Conditional Oblivious Transfer and Computing on Intervals , 2004, ASIACRYPT.

[28]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  Giles Hogben,et al.  Privacy Features: Privacy features of European eID card specifications , 2008 .

[30]  Juan A. Garay,et al.  Practical and Secure Solutions for Integer Comparison , 2007, Public Key Cryptography.