A Survey: An Effective Utilization of Machine Learning Algorithms in IoT Based Intrusion Detection System
B. K. Natarajan, Sanjay K. Bose, N Maheswaran, G Logeswari, T Anitha
Abstract
With tremendous advancements in technologies, the life has become easier while on other end, security issues pose a serious threat. Cyberattacks have increased by multiple folds due to drastic evolution of internet in the past decade. In this background, Intrusion Detection System (IDS) is one of the protective layers that safeguard the interests of internet consumers. IDS offer a safe zone for consumers in general and company owners so they may go about their daily business uninterrupted by malicious network activity. In recent times, Machine Learning (ML) algorithms are increasingly applied to find and categorize the security threats. The current research article conducts a comparison of EffectivE Utilization of Machine Learning Algorithms(EUMLA) implemented in IDS so far, for various applications like IoT, cloud services, big data, 5G network and smart cities. Further, the current work also aims at intrusion classification with the help of ML algorithms such as Classification and Regression Trees (CART), LDA (Linear Discriminant Analysis) and Random Forest algorithms. The KDD-CUP dataset was used to validate the proposed model, and its performance was analyzed and compared to other methodologies.