A Secure Keyword Spotting Scheme Based on Complex Residual Network
Jingyi Chen, Xiangyu Gao, Peijia Zheng, Huiyu Zhou, Jian Li, Dong‐Qing Wei, Jianbin Zou · 2024
To address the privacy risks associated with intelligent voice assistants, this paper proposes a non-interactive, end-to-end keyword spotting scheme in the encrypted domain. The scheme introduces an innovative complex-valued residual neural network (CR-NN) and leverages low-degree polynomial approximations to enable encrypted computation of complex activation functions. By supporting single instruction multiple data (SIMD) operations, the scheme significantly enhances computational efficiency while reducing ciphertext size. Experimental results demonstrate that the proposed method outperforms existing approaches across multiple performance metrics, balancing efficient keyword spotting with robust privacy protection and offering new insights for the application of deep learning in the encrypted domain.