Secure Face Matching Using Fully Homomorphic Encryption
By Vishnu Naresh Boddeti. 2018
147 citations recorded by the source corpus.
Face recognition technology has demonstrated tremendous progress over the past few years, primarily due to advances in representation learning. As we witness the widespread adoption of these systems, it is imperative to consider the security of face representations. In this pa per, we explore the practicality of using a fully homomorphic encryption based framework to secure a database of face templates. This framework is designed to preserve the privacy of users and prevent information leakage from the templates, while maintaining their utility through tem plate matching directly in the encrypted domain. Additionally, we also explore a batching and dimensionality reduction scheme to trade-off face matching accuracy and computational complexity. Experiments on benchmark face datasets (LFW, IJB-A, IJB-B, CASIA) indicate that secure face matching can be practically feasible (16KB template size and 0.01 sec per match pair for 512-dimensional features from SphereFace I231) while exhibiting minimal loss in matching performance.
Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, 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
- Ramesh Raskar
- Praneeth Vepakomma
- Fatemehsadat Mirshghallah
- Hadi Esmaeilzadeh
- Abhishek Singh
- Mohammadkazem Taram
- Luc Van Gool
- Radu Timofte
In Electrical and Electronic Engineering
- Hadi Esmaeilzadeh
- Ramesh Raskar
- Fatemehsadat Mirshghallah
- Abhishek Singh
- Mohammadkazem Taram
- Praneeth Vepakomma
- Sparsh Mittal
In Signal Processing
- Hadi Esmaeilzadeh
- Ramesh Raskar
- Fatemehsadat Mirshghallah
- Abhishek Singh
- Mohammadkazem Taram
- Praneeth Vepakomma
Citations in the corpus
- NoPeek: Information leakage reduction to share activations in distributed deep learning (2020, neutral): “The work in [39, 40, 41] describes HE and garbled circuits (an MPC scheme) for privacy-preserving biometric identification.”
- Privacy in Deep Learning: A Survey (2020, methodology): “ARDEN [106] # # # MNIST, CIFAR-10, SVHN Image Classification w/ DNN Cloak [107] # # CIFAR-100, CelebA, UTKFace Image Classification w/ DNN Cryptonets [108] # # # MNIST Image Classification w/ DNN Private Classification [109] # # # MNIST Image Classification w/ DNN TAPAS [110] # # # MNIST, Faces, Can”
- Towards Deep Neural Network Training on Encrypted Data (2019, unknown): “More recently, protocols for secure face matching [3] and secure k-nearest neighbor search [27] have been proposed based on fully homomorphic encryption.”