Deep Quaternion Features for Privacy Protection

2020/03/18 by Hao Zhang, Zhang, Hao, Yi-Ting Chen +9
Computer Science · #Adversarial Robustness in Machine Learning #Chaos-based Image/Signal Encryption #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2003.08365

openalex publication_date 2020/03/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Gradient-based learning applied to document recognition
• ImageNet classification with deep convolutional neural networks
• Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment
• Quaternion Recurrent Neural Networks
• Learning Multiple Layers of Features from Tiny Images

Related

• Rotation-Equivariant Neural Networks for Privacy Protection
• Interpretable Complex-Valued Neural Networks for Privacy Protection
• A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component
• Privacy-preserving Learning via Deep Net Pruning
• Industrial Scale Privacy Preserving Deep Neural Network