移动商务推荐系统中的一种基于P2P的隐私保护策略  

P2P-based Privacy Protection Strategy in Mobile-commerce Recommender System

作　　者：王利娥[1,2] 许元馨 李先贤[1,2] 刘鹏[1,2] 

机构地区：[1]广西师范大学广西多源信息挖掘与安全重点实验室,桂林541004 [2]广西师范大学计算机科学与信息工程学院,桂林541004

出　　处：《计算机科学》2017年第9期178-183,共6页Computer Science

基　　金：国家自然科学基金(61662008;61672176;61502111);广西区域多源信息集成与智能处理协同创新中心;广西自然科学基金(2015GXNSFBA139246);"八桂学者"工程专项经费资助

摘　　要：近年来,移动推荐系统已成为推荐系统研究领域最活跃的课题之一。但由于移动终端的私人性和移动网络的复杂性,在保证高精度推荐的同时如何保护用户隐私已经成为移动商务发展的主要挑战。传统推荐系统中的隐私保护技术由于移动终端的计算能力差、无线网络的带宽弱等局限无法适用于移动商务推荐系统。针对以上问题,面向移动商务推荐提出一种基于P2P的隐私保护策略,通过构建P2P好友圈,采用基于k-匿名的代理转发的增量数据更新方式,实现不对增量数据进行任何修改以保证高精度推荐,同时保护用户隐私安全。最后通过实验验证了基于P2P的隐私保护策略的可行性和推荐服务的有效性。Mobile recommender systems have recently become one of the hottest topics in the domain of recommender systems. How to provide high-precision recommendations and privacy protection has become the main challenge in the development of mobile-commerce, since mobile device is privacy and mobile network is complex. Due to its weakness of computation power and bandwidth, recommender system of mobile-commerce is not able to use these privacy-preserving techniques which are initially designed for traditional recommender systems. To address above problems, a P2P-based privacy protection approach specifically for mobile-commerce recommender system was proposed in this paper. Our ap- proach keeps incremental data intactiy for guaranteeing high-precision recommendations while preserving privacy by constructing friends＇ circles and forwarding data anonymously based on the model of k-anonymity. In the end, the ex- periment shows that the P2P-based privacy protection approach is feasible and effective.

关 键 词：P2P 移动商务推荐系统 隐私保护 K-匿名 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]