Wireless network confidence level improvement via fusion adaptive resonance theory

Abstract

One of the main hazards for the current internet community is the distributed denial of service attack (DDoS). Moreover, with the DDoS mechanisms being implicit in nature, the identification of it is very hard due to the unique characteristics of the normal traffic and useless packet sent to their victims by adversaries. The vulnerability of network mechanisms (VNM) accounts for maximal performance degradation on the system by the malicious users with the abundance resource availability. In addition, the Hash table based VNM suffers from longer waiting time with the attack size reflecting on the duplicate effect on the vulnerability. Rule-based firewall’s performance is evaluated by an analytical Queuing model that are exposed to standard traffic and DDoS attack flows where this model is based on embedded Markov chain (EMC). Queuing model based on EMC targets the different rule positions but mitigate DDoS attacks targeting bottom rules with minimal confidence in the network. To attain the confidence in the network, adaptive resonance theory (ART) is applied based on the semantic similarity measure. Furthermore, for learning inherent associations, a fusion method on the ART network is deployed. Fusion ART uses the multiple overlapping ART models. In this clusters are generated and associative mappings are coded transversely packet information in a real-time and continuous way. Semantic similarity category is combined in a fusion ART into predefined semantic categories to attain maximal confidence value in the network. ART scheme increases the trusted platform module by preventing the unnecessary DDoS attack. Fusion ART functionalities through ns2 simulation, produces the positive solution measured in terms of confidence rate in network, waiting time, CPU utilization, true positive rate, throughput.