IT Attack Detection and Classification using Users Event Log Feature And Behavior Analytics through Fourier EEG Signal

As the documentary action of every single enterprise and government agencies are being digitalized and several industries are heading towards complete Migration towards virtualization the risk of security threat, malicious attacks, criminal mindset are arising. Deep learning and AI have always been setting a new paradigm in one step above detection and classification of several attacks based on its file and features. Several enterprises utilize the historic data of their employees for storing cookies and understanding business processes. In this paper, we are proposing a new framework in which Malicious attacks can be classified using anomaly detection based on event users' log similarities and summaries of operations performed virtually. Also, the Classification of these relevant features log using Decomposed EEG signal is shown for detecting behavior more precisely using Kruskal- Wallis algorithm has been employed to select explicit static features. These selected features are used to classify the given EEG dataset into different categories using a supervised EEG decomposition algorithm.