医疗辅助诊断系统中新型的双向隐私保护方法

为了保护医疗辅助诊断系统中患者的个人隐私,本文提出一种新的结合决策树与不经意传输(Oblivious Transfer, OT)技术的双向隐私保护方法.该方法首先利用决策树对已有诊断信息进行分类来形成辅助诊断,并利用差分隐私确保决策树构建过程中不会泄露数据库的隐私.其次利用OT技术保护查询过程中的隐私,并提出一种决策树索引协议将决策树算法与OT协议有效结合.提出的方法最早将决策树与OT技术应用于医疗辅助诊断系统,并且在客户端进行医疗数据查询并得到准确查询结果的情况下,能够极好地保护客户端、服务器以及数据库的隐私信息,实现更全面的双向隐私保护.理论分析结果表明,本文提出的方法在保护隐私的同时具有较高的通信效率.进一步地,实验结果也表明,提出的方法不仅具有较高的查询效率,同时还具有较高的查询准确率.

Novel Two-Way Privacy Protection Method in Medically Assisted Diagnosis System

In order to protect the personal privacy of patients, a novel two-way privacy protection method in medically assisted diagnosis system that combines decision trees and oblivious transfer(OT) is proposed. The proposed method utilizes the decision tree to classify the existing diagnosis information to form an auxiliary diagnosis. In order to realize the two-way privacy protection in the query process, this paper uses differential privacy to add noise to the decision tree to ensure that the privacy of database will not be leaked during the construction of the decision tree. In order to effectively combine the decision tree algorithm with the OT protocol, a decision tree indexing protocol is proposed that can efficiently digitize the decision tree. The proposed protocol facilitates the use of the OT protocol to protect the privacy of the client, while ensuring that the client can only get the query related information, thereby protecting the privacy of the server. The proposed method applies decision tree and OT technology to medical assisted diagnosis systems. It protects the sensitive information of a client, a server and a database when the client performs medical data query and obtains accurate query results, hence can provide more comprehensive two-way privacy protection. The theoretical analysis results show that the proposed method protects privacy with high communication efficiency.Furthermore, the experimental results also show that the proposed method has high query efficiency and high query accuracy.