ARBA:基于分解重构技术的LBS隐私保护方法  

A novel anonymization method based on anatomy and reconstruction in LBS privacy preservation

作　　者：林瑜[1] 韩建民[1] 于娟[2] 贾泂[1] 詹皇彬 

机构地区：[1]浙江师范大学数理与信息工程学院,浙江金华321004 [2]复旦大学计算机科学与技术系,上海200433

出　　处：《中国科学技术大学学报》2014年第7期544-553,562,共11页JUSTC

基　　金：国家基金项目(61170108;6110019);浙江省自然科学基金(Y1100161;LQ13F020007)资助

摘　　要：现有的匿名化方法多采用时空伪装技术,该技术计算负担重,LBS响应延迟时间长,导致LBS服务质量低.为此,提出了分解重构的匿名化方法,该方法首先对接收到的LBS查询集进行分组,形成满足匿名模型的等价类,然后对每个等价类根据不同的策略进行分解和重构,生成新的匿名查询集.此外,面向多种隐私需求,提出了一系列匿名模型,并进一步提出了基于分解重构技术的匿名模型的实现算法MBFAA.实验表明,提出的重构分解技术可以有效地实现各种匿名模型.Most of the existing methods are realized by temporal and spatial cloaking techniques .However , these cloaking-based methods are disadvantageous due to their high computation loads and long response delays ,which lowers service quality . To address these problems , a novel technique , anatomy and reconstruction ,was proposed .This technique first partitions the LBS query set into several equivalence classes , making sure that each equivalence class satisfies the given anonymity constraints . T hen it reconstructs the LBS queries in each equivalence class according to the predefined strategies separately , and generates a new set of anonymous queries .Considering various privacy requirements ,a series of anonymity models were proposed , and a unified anonymization algorithm MBFAA was introduced to realize these models . Experimental results show that the proposed method can effectively implement all the anonymity models .

关 键 词：K-匿名 位置 l-多样性 查询 m-多样性 分解重构 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]