Enhancing Cybersecurity Through Machine Learning-based Anomaly Detection in IoT Environments

Thesis Abstract

Abstract


As the Internet of Things (IoT) continues to proliferate, the security challenges associated with interconnected devices become increasingly pronounced. This research endeavors to enhance cybersecurity by leveraging machine learning-based anomaly detection in IoT environments. The study encompasses a thorough review of cybersecurity threats, the pivotal role of machine learning, and contemporary anomaly detection techniques. Special emphasis is placed on understanding the intricacies of the IoT landscape, exploring common threats, vulnerabilities, and regulatory frameworks. The core of the research involves the development and evaluation of a machine learning-based anomaly detection system tailored for IoT, addressing issues of real-time detection, interpretability of models, and practical implementation challenges. The findings contribute to the ongoing discourse on bolstering cybersecurity measures in the dynamic and intricate realm of IoT.