Detection and classification of covert channels in IPv6 using enhanced machine learning
Ali Khalil Salih, Xiaoqi Ma, Evtim Peytchev · Nottingham Trent University's Institutional Repository (Nottingham Trent Repository) · 2015
Zero day Cyber-attacks created potential impacts on the way information is held and protected, however one of the vital priorities for governments, agencies and organizations is to secure their network businesses, transactions and communications, simultaneously to avoid security policy and privacy violations under any circumstances.Covert Channel is used to in/ex-filtrate classified data secretly, whereas encryption is used merely to protect communication from being decoded by unauthorized access.In this paper, we propose a new Machine Learning approach to detect covert channel implementing an enhanced feature selection algorithm supporting Naive Bayesian classifier.NBC is one of the most prominent classification algorithm defining the highest probability in data mining area.The proposed framework uses Intelligent Heuristic Algorithm (IHA) to create novel primary training data, in addition to a modified Decision Tree C4.5 technique to detect and classify hidden channels in IPv6 network.The results showed better detection performance and high accuracy in True Positive Rate (TPR) and a low false negative rate (FNR) in comparison to other previous techniques.