期刊名称：International Journal of Security and Its Applications
印刷版ISSN：1738-9976
出版年度：2016
卷号：10
期号：12
页码：173
出版社：SERSC
摘要：detection under Cloud computing environmentplays an important role in detecting anomalous virtual machines (VMs) before real failures occur. In order to accurately characterize the newtrend of VMs' performance, new samples are collected, detected, and selectively added into the training sample set.The newly added samples are used forupdatingthe detectionmodel, so as to improvedetection accuracy.However, increasing number of training samplescauses both much storage spaceand CPUtime. To overcome this challenge, this article proposes an anomaly detection algorithm based on online learning Lagrangian SVM (termed OLLSVM) for detecting anomalousVMs. Online learning includes incremental learningand decremental learning. Single-sampleand batch incremental learningalgorithms are designed to update the detection model whenadding a single sample or a set of samples.Similarly, single-sampleand batch decremental learning algorithms aredesigned for deleting a single sample or a set of samples. The strategies for selecting sample(s) to be added or deleted are also designed. This article conducts experiments on Cloud datasets and KDD Cup datasets. The experimental results show that, compared with traditional Lagrangian SVM(LSVM) which retrains the detection model each time when adding or deleting sample(s), OLLSVM achieves almost similar high detection accuracy but much higher time efficiency.
