Efficient Privacy-Preserving Face Recognition

By Ahmad-Reza Sadeghi, Thomas Schneider, Immo Wehrenberg. 2009

390 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Privacy-Preserving Ridge Regression on Hundreds of Millions of Records (2013, methodology): “Similar to our system, some works introduced hybrid approaches, such as combining HE and garbled circuits for face and fingerprints recognition [51], [52], and combining secret sharing with garbled circuits for learning a decision tree [53].”
Gazelle: A Low Latency Framework for Secure Neural Network Inference (2018, methodology): “We are aware of one system [34] that tries to use Paillier in a SIMD fashion; however, this lacks two crucial components of lattice-based AHE, namely the facility to multiply each slot with a separate scalar, and the facility to permute the slots.”
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications (2018, background): “There are many applications in privacy-preserving biometric authentication [17, 37, 38, 71, 76], secure auctions [39], privacy-preserving machine learning [35], and data mining [59, 60, 69].”
More efficient oblivious transfer and extensions for faster secure computation (2013, background): “, for face recognition [15, 55], finger code authentication [2], or online marketplaces [10].”
Faster Secure Two-Party Computation Using Garbled Circuits (2011, background): “Beginning with Fairplay [22], several implementations of generic secure two-party computation have been developed in the past few years [11, 21, 27] and used to build privacy-preserving protocols for various functions (e.g., [4,13,16,26,29]).”
Privacy-preserving matrix factorization (2013, methodology): “For this reason, we adopt a hybrid approach, combining public-key encryption with garbled circuits, as in [57, 50].”
Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference (2020, neutral): “A classic solution is to combine multiple cryptographic solutions, as done before in [37], [39], [42], [46], [54], and partition inferences across them.”
Handbook of Face Recognition, 2nd Edition (2011, background): “Companies such as PolarRose are seeking to apply these techniques to social network sites, and companies such as Google are applying face recognition technologies to label photographs and videos [44] of celebrities on the web.”
ABY2.0: Improved Mixed-Protocol Secure Two-Party Computation (2020, methodology): “Since Maxpool/Minpool is an essential building block for several applications like K-means clustering [25], face-recognition [93], and fingerprint-matching [15, 43], we provide a separate analysis for Maxpool in §6.”