Edge and Cloud-aided Secure Sparse Representation for Face Recognition
Yitu Wang, Takayuki Nakachi, Hiroyuki Ishihara · 2019
Edge and cloud computing has recently emerged not only to meet the ever-increasing computation demands, but also to provide extra degree of diversity by collecting data from the mobile devices in service. However, this, in turn, has raised new technical challenges on the security issue, and calls for the design of new frameworks to exploit multi-device diversity. In this paper, we take the advantage of this benefit while preserving the privacy. Specifically, 1). To address the privacy issue, we develop a low-complexity encrypting algorithm based on random unitary transform, where it is proved both theoretically and through simulation that such encryption will not affect the result of face recognition. 2). To exploit multi-device diversity, we integrate the recognition results based on the dictionaries of each device into an aggregated output through ensemble learning, which has shown higher correctness of predictability than any individual methods. The designed framework not only contributes to the reduction of computation complexity at each device, but also proves to be effective and robust through simulation results.