Abstract: At present, Camouflaging worm attack constitute a large part of internet peer servers. Due to the increasing traffic in internet services, it has become inevitable to take into account its effects on network management. Generally, studies on resisting Camouflaging Worm attack have involved analysis with power spectral density distribution via spectrum-based scheme. However, with several facilities provided by spectrumbased scheme, its network traffic volume in internet severs is increasing day by day increasing the malicious traffic rate. In this research proposal plan is to develop efficient identification of C-Worm propagation and restriction of uncontrolled malicious traffic in the internet by applying Enhanced Hidden Markov Chain-based C-Worm Detection (EHMC-CWD) technique. The C-Worm replicates the abnormal traffic on its own and propagates throughout the network and cause damages to the internet services. Enhanced Hidden Markov Chain (EHMC) identifies the camouflaging abnormal traffic replicated across the internet. Next, EHMC adapted a dynamic Bayesian network to evaluate camouflaging worm propagation by means of optimal non linear filtering. Therefore the replicated traffic generated by C-Worm reveals the information about the sequence of traffic in which it is propagated. The performance of EHMC-CWD is evaluated by extensive simulations. Simulation results show that our proposal can considerably reduce the execution time for C-Worm detection and memory space and also improves high detection rate to a certain degree.
R. Saranya and S. Senthamarai Kannan, 2016. An Enhanced Hidden Markov Dynamic Bayesian model for Resisting Camouflaging Worm attack study. Asian Journal of Information Technology, 15: 3616-3623.