Adaptive Worm Detection Model Based on Multi Classifiers

Abstract

Security has become ubiquitous in every area of malware newly emerging today pose a growing threat from ever perilous systems. As a result to that, Worms are in the upper part of the malware threats attacking the computer system despite the evolution of the worm detection techniques. Early detection of unknown worms is still a problem. In this paper, we proposed a "WDMAC" model for worm's detection using data mining techniques by combination of classifiers (Naïve Bayes, Decision Tree, and Artificial Neural Network) in multi classifiers to be adaptive for detecting known/ unknown worms depending on behavior-anomaly detection approach, to achieve higher accuracies and detection rate, and lower classification error rate. Our results show that the proposed model has achieved higher accuracies and detection rates of classification, where detection known worms are at least 98.30%, with classification error rate 1.70%, while the unknown worm detection rate is about 97.99%, with classification error rate 2.01%.

Network Intrusion Detection Using Semi-Supervised Learning Based on Normal Behaviour's Standard Deviation

“…Barhoom and Qeshta 2013 [15] proposed a new approach based on data mining techniques for worm's detection; using a combination of classifiers (Naïve Bayes, Decision Tree, and Artificial Neural Network) in order to be adaptive for detecting known/unknown worms, to achieve higher accuracies and detection rate, and lower classification error rate. The results show that the proposed model has achieved higher accuracies and detection rates of classification, where detection known worms are at least 98.30%, with classification error rate 1.70%, while the unknown worm detection rate is about 97.99%, with classification error rate 2.01%.…”