Scrutinization of Threats from a Cloud-based Network Traffic Environment

In this age of digitalization, securing computer networks is of utmost importance to protect sensitive data and critical infrastructure. Threat scrutinization plays an integral role in identifying and thwarting cyber risks. This study focuses on a pioneering strategy to bolster the network’s reliability by harnessing Artificial Intelligence (AI) techniques in conjunction with cloud computing infrastructure, particularly AWS SageMaker. The focus lies in leveraging a comprehensive and realistic cyber dataset, CSE-IDS-2018, to assess the efficacy of the proposed model. The study commences by architecting a threat scrutinization mechanism that harnesses the feasibility of machine learning algorithms, deep learning models, and cloud computing resources. Specifically, the Random Forest algorithm is employed for the multi-class classification of seven types of attacks within the CSE-CICIDS2018 dataset, facilitated by AWS SageMaker’s machine-learning capabilities.