A Scalable, Lightweight AI-Driven Security Framework for IoT Ecosystems: Optimization and Game Theory Approaches
Year: 2025
Type: article
Abstract: The development of the Internet of Things (IoT) has been impressive, fostering connectivity for applications while exposing new and growing security issues such as scalability issues. Such concerns are not considered hard by traditional security models since devices overload the current systems, and most technologies are only reactive rather than proactively changing results among IoT devices. The framework suggested in this paper is composed of a three-layer solution concept based on AI-IDS, Blockchain, and Edge Computing. Threats are countered with machine learning triggers, while blockchain is implemented to improve data flow accuracy in IoT systems. The edge computing issue considers that data processing surrounds IoT devices, which can enhance resources and effectiveness in poor network scenarios. The study, therefore, uses optimization strategies for enhancing system performance, game theory in representing the relationship between IoT objects and security personnel and differential equations for simulating dynamic behaviors of the IoT system under attack. It is then compared to conventional passive models where the improvements in scale, speed, and response time are demonstrated. The proposed approach can be considered a self-contained, self-learning, fundamentally scalable approach to addressing emerging and continually metamorphosing IoT cyber threats by improving the security and steadiness of IoT networks, particularly in restrained contexts.
Source: IEEE Access
Author: Krishna Chaitanya Chaganti
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W4409223191