云计算下多属性信息交换安全漏洞识别仿真

Multi-Attribute Information Exchange Security Vulnerability Recognition Simulation under Cloud Computing

传统信息交换漏洞识别方法仅适用于单属性信息,其应用局限性较大。为解决上述问题,在云计算背景下提出一种多属性信息交换安全漏洞识别方法。利用无监督方式组建原始数据支持向量机模型,通过主动学习策略获取漏洞识别性能高价值样本进行人工标记,标记数据以及未标记数据通过半监督的形式对基于支持向量机的多属性信息交换进行拓展,结合云计算主动学习选取较小的标记代价完成模型的性能优化,实现云计算下多属性信息交换安全漏洞识别。为验证所提方法的有效性,进行一次仿真。实验结果表明,所提方法能够有效提升多属性信息交换安全漏洞识别准确性以及效率,有效增强所属性信息交换系统的安全性。

The traditional information exchange vulnerability identification method is only suitable for single-attribute information, and its application is limited. Therefore, a multi-attribute information exchange security vulnerability identification method is proposed under the background of cloud computing. A support vector machine(SVM) model of original data was built in an unsupervised way. Through active learning strategy, high-value sample of vulnerability identification performance was obtained and marked manually. In the form of semi-supervision, marked data and unmarked data were used to expand the multiple attribute information exchange based on support vector machine(SVM). Combined with Cloud computing active learning, the smaller cost was chosen to complete the performance optimization of model. Finally, the identification of multiple attribute information exchange security hole in the background of cloud computing was achieved. In order to verify the effectiveness of the proposed method, a simulation was carried out. Experimental results show that the proposed method can effectively improve the accuracy and efficiency of identification, and effectively enhance the security of information exchange system.