Research on virus detection technique based on ensemble neural network and SVM

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