网络海量数据中隐私泄露检测方法仿真

Simulation of Privacy Leak Detection Method for Massive Network Data

研究网络海量数据中隐私泄露准确检测问题。在网络海量数据环境下,数据量十分巨大,查询哪些数据存在泄露风险,需要根据数据结构进行轮番查询。传统的泄露查询检测方法需要根据网络中的所有历史查询结果建立查询数据结构,在网络数据规模较大的情况下,造成数据结构过于庞大,泄露检测过程耗时过大。提出基于相空间重构算法的网络海量数据中隐私泄露检测方法。通过被动响应方式,获取网络海量数据中的隐私泄露数据特征,获取对应的特征分解矩阵,计算隐私泄露数据平衡特征,并对上述特征进行整合。将上述特征映射到高维特征空间,获得最优线性回归函数,得到隐私泄露检测线性回归模型,简化检测过程。实验结果表明,利用改进算法进行网络海量数据中隐私泄露检测,可以提高检测效率,缩短检测时间。

This paper studied the accurate detection problem of privacy leak in massive network data. A detection method for privacy leak of massive network data based on phase space reconstruction algorithm was proposed. Firstly, by way of a passive response, the privacy leak characteristics of data and the corresponding feature decomposition matrix of massive network data were obtained. Meanwhile, the equilibrium characteristics of privacy data were calculated and integrated. Finally, the above features were mapped to high dimensional feature space, to obtain the optimal linear regression function and the linear regression model of privacy leak detection to simplify the detection process. Experimental results show that the improved algorithm in the network mass data privacy leak detection can improve the detection efficiency and shorten the detection time.