A study on the intelligent method for detection of computer viruses

This paper makes a virus detection study based on the D-S theory of evidence, which applies to two types of classifiers, support vector machines and probabilistic neural networks to detect the virus. Then, the D-S theory of evidence is used to combine the contribution of each individual classifier to obtain the final decision. The experiment tests and result analyses demonstrate that it is efficient for unknown viruses and variant viruses to improve accuracy rate of integration virus detector by using D-S theory to create the isomeric classifier.