2020/03/18 by Hao Zhang, Zhang, Hao, Yiting Chen +10 · 9 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Artificial intelligence #Artificial neural network #Chaos-based Image/Signal Encryption #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Construct (python library) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Layer (electronics) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mathematics #Privacy-Preserving Technologies in Data #Quaternion #cs.CR #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2003.08365
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2020/03/18 · arxiv created 2020/06/21 · arxiv updated 2020/06/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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.