期刊名称：International Journal of Security and Its Applications
印刷版ISSN：1738-9976
出版年度：2015
卷号：9
期号：7
页码：153-162
DOI：10.14257/ijsia.2015.9.7.14
出版社：SERSC
摘要：In recent years, cloud computing is becoming popular in the field of information, however, the development of cloud computing have to face the problem of cloud security. Intrusion Deletion System (IDS) is one of the possible solutions to the problem of cloud security, but the correct rate of general application of the IDS is not very satisfactory, for this purpose we propose a density-based binary Support Vector Machine (SVM) method (D-BSVM). Its main idea is based on the density of each class in the data set, and gets a binary sequence of training, according to this sequence obtained binary SVM training model to predict the behavior of the system. Further, the method for calculating the density is the paralleled, thereby improving efficiency of overall system. Finally, we present experimental results, and by contrast our approach can improve the accuracy and detection rate of IDS.
