Predicting the Discovery Pattern of Publically Known Exploited Vulnerabilities

Vulnerabilities with publically known exploits typically form 2-7% of all vulnerabilities reported for a given software version. With smaller number exploited compared the total vulnerabilities, it is more difficult to model and predict when vulnerability exploit will be reported. In this paper, we introduce an approach predicting discovery pattern using software. Eight commonly used models (VDMs) one neural network (NNM) were utilized evaluate prediction capability our approach. We their predictions results scenario only prediction. Our show that, in terms accuracy, out eight analyzed, led accurate seven cases. Only case, accuracy was worse by 1.6%.