IEEE Transactions on Information Forensics and Security · 2013 · 64 citations · 21 references
ComputingComputer ScienceCybersecurityComputer VisionCryptographyMachine LearningData ProtectionFace RecognitionHomomorphic EncryptionPattern RecognitionPrivacy-preserving ProtocolsSecure Multi-party ComputationAccuracyFace VerificationFully Homomorphic EncryptionGabor FeaturesLloyd-max QuantizationPrivacyPrivacy-preserving Face RecognitionSoft Margin Svm
Face recognition is one of the foremost applications in computer vision, which often involves sensitive signals; privacy concerns have been raised lately and tackled by several recent privacy-preserving face recognition approaches. Those systems either take advantage of information derived from the database templates or require several interaction rounds between client and server, so they cannot address outsourced scenarios. We present a private face verification system that can be executed in the server without interaction, working with encrypted feature vectors for both the templates and the probe face. We achieve this by combining two significant contributions: 1) a novel feature model for Gabor coefficients' magnitude driving a Lloyd-Max quantizer, used for reducing plaintext cardinality with no impact on performance; 2) an extension of a quasi-fully homomorphic encryption able to compute, without interaction, the soft scores of an SVM operating on quantized and encrypted parameters, features and templates. We evaluate the private verification system in terms of time and communication complexity, and in verification accuracy in widely known face databases (XM2VTS, FERET, and LFW). These contributions open the door to completely private and noninteractive outsourcing of face verification.
21
Matthew Turk, Alex Pentland · Journal of Cognitive Neuroscience · 1991 · 13.8K citations · Full text
Factoring polynomials with rational coefficients
A. K. Lenstra, H. W. Lenstra, László Lovász · Mathematische Annalen · 1982 · 4K citations · Full text
A fully homomorphic encryption scheme
Dan Boneh, Craig Gentry · 2009 · 2.4K citations
Quantizing for minimum distortion
J. Max · IEEE Transactions on Information Theory · 1960 · 2.1K citations