click here to download project abstract/base paper of Nearest Neighbor Search
ABSTRACT
Medical imaging is crucial for medical diagnosis, and the sensitive nature of medical images necessitates rigorous security and privacy solutions to be in place. In a Healthcare Industry 4.0 cloud-based medical system, it is imperative to encrypt medical images before outsourcing them. However, processing queries over encrypted data without first executing the decryption operation is challenging and impractical at present.
In the paper, we propose a secure and efficient scheme to find the exact Nearest Neighbor Search over encrypted medical images. Instead of calculating the Euclidean distance, we reject candidates by computing the lower bound of Euclidean distance that is related to the mean and standard deviation of data. Unlike most existing schemes, our scheme can obtain the exact nearest neighbor rather than an approximate result. We then evaluate our proposed approach to demonstrate its utility.
INTRODUCTION
CLOUD computing is becoming a norm in our society [1], and in such a deployment, the data owner can outsource databases and management functionalities to the cloud server. The latter stores the databases and supplies access mechanisms to query and manage the outsourced database. This allows data owners to reduce data management expenses and improve quality of service. However,
full trust in the cloud may not be warranted, as it has the potential to disclose sensitive information to unauthorized entities, such as compromised individuals or foreign government agencies.
The rapid evolution of cloud computing is revolutionizing e-Health and the whole Industry 4.0 in the field of healthcare. The cloud-based electronic healthcare system is one popular application for Healthcare Industry 4.0. The National Natural Science Foundation of China supports this paper under grant No. 61501080, 61572095, and 61871064. Additionally, the Cloud Technology Endowed Professorship and NSF CREST provide partial support under Grant HRD-1736209. This paper asserts that a well-designed electronic healthcare system can evidently enhance quality.
