Date of Award
8-1-2024
Degree Name
Master of Science
Department
Computer Science
First Advisor
Hexmoor, Henry
Second Advisor
Gupta, Bidyut
Abstract
The proliferation of IoT devices in various sectors, such as healthcare, industrial systems, and residential areas, presents unique security vulnerabilities that conventional security frameworks struggle to address. This research explores how ML techniques can be leveraged to enhance IoT security, offering adaptive, robust, and efficient solutions. A thorough literature review identifies the intersection of ML and IoT security, emphasizing the need for dynamic and resilient security mechanisms that can anticipate and mitigate emerging threats. The study presents several case studies, including the deployment of ML in securing smart home systems and healthcare infrastructures, demonstrating the practical application and benefits of integrating ML into IoT security frameworks. Significant findings from these case studies illustrate the effectiveness of ML-driven security systems in detecting anomalies, enhancing data protection, and providing real-time threat detection. However, challenges such as data scarcity, privacy concerns, and the need for continuous model refinement remain prevalent. The thesis contributes to the academic and practical understanding of IoT security by providing detailed insights into the current capabilities and limitations of ML applications in this area. It also outlines future research directions focusing on the development of advanced ML algorithms, privacy-preserving techniques, and standardized approaches for improving the security and efficiency of IoT systems
Access
This thesis is only available for download to the SIUC community. Current SIUC affiliates may also access this paper off campus by searching Dissertations & Theses @ Southern Illinois University Carbondale from ProQuest. Others should contact the interlibrary loan department of your local library or contact ProQuest's Dissertation Express service.