Implementation of Machine Learning in Network Security

Abstract

Machine learning (ML) is prevalent across the globe and applied in almost all domains. This chapter focuses on implementation of ML with real-time use cases. Day-to-day activities are automated to ease the task and increase the quality of decision. ML is the backbone of the perfect decision support system with a plethora of applications. The use case described in this chapter is ML & Security, which is implemented in R Script. Adversaries took advantages of ML to avoid detection and evade defenses. Network intrusion detection system (IDS) is the major issue nowadays. Its primary task is to collect relevant features from the computer network. These selected features can be fed into the ML algorithms to predict the label. The challenge in this use case is what type of feature to consider for intrusion and anomaly detection (AD). This chapter focuses on end-to-end process to get insight into the stream of data from the network connection with priority given to forecasting mechanism and prediction of the future. Forecasting is applied to the time series data to get sensible decisions.