A Privacy-Preserving Learning Framework for Face Recognition in Edge and Cloud Networks
Yitu Wang, Takayuki Nakachi
Abstract
Offloading the computationally intensive workloads to the edge and cloud not only improves the quality of computation, but also creates an extra degree of diversity by collecting information from devices in service. Nevertheless, significant concerns on privacy are raised as the aggregated information could be misused without the permission by the third party. Sparse coding, which has been successful in computer vision, is finding application in this new domain. In this paper, we develop a secured face recognition framework to orchestrate sparse coding in edge and cloud networks. Specifically, 1). To protect the privacy, a low-complexity encrypting algorithm is developed based on random unitary transform, where its influence on dictionary learning and sparse representation is analysed. Furthermore, it is proved that such influence will not affect the accuracy of face recognition. 2). To fully utilize the multi-device diversity and avoid big data transmission between edge and cloud, a distributed learning framework is established, which extracts deeper features in an intermediate space, expanded according to the dictionaries from each device. Classification is performed in this new feature space to combat the noise and modeling error. Finally, the efficiency and effectiveness of the proposed framework is demonstrated through simulation results.