【摘要】 针对轨迹数据隐私保护中数据可用性低及易受语义推断攻击问题,提出一种基于敏感语义位置的轨迹隐私保护算法。该算法利用Voronoi图将语义位置预先划分为独立的Voronoi单元,再依据语义位置流行度以及用户设定的敏感语义位置类型、语义安全阈值对轨迹停留位置进行空间匿名,构建语义安全匿名区域,防止语义推断攻击和提高数据可用性。实验结果表明,与其他算法相比,所提算法在信息损失率上平均降低约30%,算法运行时间上平均降低约30%。更多还原

【Abstract】 Aiming at the problems of low data availability and vulnerability to semantic inference attacks in trajectory data privacy protection,a trajectory privacy protection algorithm based on sensitive semantic position is proposed. The algorithm uses Voronoi diagram to divide the semantic location into independent Voronoi units in advance,and then according to the sensitive semantic location type,semantic security threshold and semantic location popularity set by the user,spatial anonymity is used to construct the semantic security anonymous area to prevent semantic inference attacks and improve data availability.Experimental results show that,compared with other algorithms,our algorithm has an average reduction in information loss rate of about 30% and an average reduction in algorithm running time of about 30%.更多还原