A convolutional neural network based model with improved activation function and optimizer for effective intrusion detection and classification

Abstract

In today's world, technological advancements have entangled our nancial, social and many more other aspects of lives to the internet or some network. Moreover, with the development of IoT technologies, it has spread over to our transportation, home-appliances and more devices. It is also a security risk because all of our sensitive and private knowledge on the Internet is exposed to a growing amount of cyber-attacks. An Intrusion Detection System can identify a cyber-attack while it is ongoing or prior to it. We are conscious of the evolving Machine Learning and Deep Learning developments, the most sophisticated multi-functional methods created by humans that can be utilized to overcome this issue. Alongside identi fication, precise classi cation of intrusion is of considerable signi ficance for the administrator to take decisive actions. In this study, we have used the dataset CIC-IDS-2018 that is the biggest and most recent labeled dataset of intrusions. This dataset comprises of six varieties of attacks. Our thesis proposes a CNN Model with mish activation function and Ranger optimizer. The model reaches an accuracy of 0.989 that is the highest in multiclass classification with this dataset.