A SVM Model based on Network Traffic Prediction for Detecting Anomalies



Cloud computing is a natural evolution of distributed computing combined with service-oriented architecture. However, its broad adoption has been hampered due to the lack of security mechanisms. Facing this issue, this work aims to propose a new approach for detecting anomalies in the cloud network traffic. The anomaly detection mechanism works on the basis of a Support Vector Machine (SVM) model for binary classification. The key point to improve the accuracy of the SVM model, in the cloud context, is the set of features. In light of this, we present the Poisson Moving Average predictor as the feature extraction approach that is able to cope with the vast amount of information generated over time. We evaluate the performance of our mechanism and compare it against similar studies in the literature, resorting to a real case validation study.


Cloud Computing, Security, Support Vector Machine


Security on Cloud Computing


21th edition of the Portuguese Conference on Pattern Recognition, October 2015

PDF File

Cited by

No citations found