Research on Virus Detection Technology Based on Ensemble Neural Network and SVM

Computer viruses have become a serious threat to the information system. In this paper, taken ensemble learning as a guide, automatic virus detection technology is studied, where a novel approach based on the integration of dynamic virus detection and static detection is proposed. The detection system utilizes support vector machine as member classifier for viruses' dynamic behavior modeling, and also uses probabilistic neural network as member classifier for static behavior modeling. Finally, the detection results from all member classifiers are integrated by D-S theory of evidence. Through the combination of heterogeneous classifiers, the accuracy of an ensemble virus detector has been improved.