A Machine Learning Based Approaches for Detecting and Preventing Distributed DoS Attacks in IoT
Main Article Content
Abstract
For quicker reaction times, the data-driven infrastructure known as the Internet of Things (IoT) heavily relies on intelligent sensing devices. IoT devices are now susceptible to more expansive risk surfaces due to the changing cyber threats landscape, which could result in data breaches. Distributed Denial of Service (DDoS) assaults are major cyber-attacks among the many possible attacks because of their capacity to render services unusable by flooding systems with traffic. Strong DDoS detection technologies specifically designed for IoT are essential for the long-term growth of every sector that IoT serves. Since IoT devices frequently lack the built-in security features seen in more established computing platforms. As a consequence, DDoS analysis and defence are a growing area of research nowadays. The foundations of IoT, privacy and data security issues related to machine learning and IoT devices are reviewed in this paper. To limit our usage and understand the importance of protecting IoT devices in our lives, the paper also highlights current DDoS attacks and examines their effects on IoT devices. To defend against and lessen DDoS attacks on IoT devices, a strong authentication system built on machine learning techniques is needed. As a result, this review paper examines and reports on risk mitigation techniques for enhancing IoT adaptability as well as security and privacy issues.