Deep Quaternion Features for Privacy Protection
Machine Learning
2020-06-23 v2 Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
Abstract
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information. The QNN uses quaternion-valued features, where each element is a quaternion. The QNN hides input information into a random phase of quaternion-valued features. Even if attackers have obtained network parameters and intermediate-layer features, they cannot extract input information without knowing the target phase. In this way, the QNN can effectively protect the input privacy. Besides, the output accuracy of QNNs only degrades mildly compared to traditional neural networks, and the computational cost is much less than other privacy-preserving methods.
Cite
@article{arxiv.2003.08365,
title = {Deep Quaternion Features for Privacy Protection},
author = {Hao Zhang and Yiting Chen and Liyao Xiang and Haotian Ma and Jie Shi and Quanshi Zhang},
journal= {arXiv preprint arXiv:2003.08365},
year = {2020}
}