大数据环境下入侵风险评估优化模型仿真分析

Big Data Environment Risk Assessment of Optimization Model for the Simulation Analysis

针对大数据环境下的数据信息进行入侵风险评估问题。由于大数据信息环境下的数据具有动态波动的特性,使得存在大量多元数据。传统的评估方法,主要通过提取数据特征进行分类,再分别进行评估,忽略了多元数据的特征对分类产生的影响,导致评估不准确的,效率差的问题。提出改进的逆向云生成算法的大数据信息环境下的入侵风险评估建模方法。对大数据信息环境下系统的入侵危险进行感知,提取大数据信息环境下系统的正常状态云,利用逆向云生成算法获取该云的数字特征,计算被监视时刻的大数据信息环境下系统变量采样值,将计算出的采样值与正常状态云的数字特征相匹配,以匹配后的结果为依据融合抗体浓度模型进行大数据信息环境下网络入侵风险的实时评估。仿真结果表明,采用改进方法对入侵风险评估进行建模精确度高。

In this paper, we proposed a modeling method of instruction risk evaluation under big data environment based on the modified reverse cloud generation algorithm. Firstly, the method perceived the system instruction risk under big data information environment and extracted the normal state cloud. Then it used reverse cloud generation algorithm to obtain the cloud numerical characteristics and calculated the sampling values of system variables under big data information environment. Moreover, it matched the calculated sampling value and the numerical characteristics of normal state cloud. Finally, it integrated the antibody concentration model to make the real-time instruction risk e- valuation according to the matched result. The simulation results show that the model has high precision using the modified method to evaluate the instruction risk.