Distributed Denial of Services (DDoS) Botnet Attack Prevention in Internet of Things (IoT) Devices Using AI

The expeditious adoption of Internet of Things (IoT) devices has facilitated the emergence of complex cybersecurity risks, notably Distributed Denial of Service (DDoS) botnet assaults, which pose a substantial danger. With the exponential growth of interconnected devices inside the Internet of Things (IoT), the task of identifying malicious linkages becomes more challenging. The identification of these hazards has significant importance for intrusion detection systems (IDS), with the use of machine learning (ML) having been a prevailing practice due to the continuous advancement of cyberattacks. In order to effectively combat such dangers, it is essential that machine learning technologies has the capability to observe a diverse range of attack patterns, hence illustrating the intricacies involved in targeting network traffic. Regrettably, a significant portion of the datasets accessible to the machine learning community lack comprehensive representation of well recognized attack patterns. This is particularly true for datasets pertaining to Distributed Denial of Service (DDoS) attacks, such as ACK and PUSH-ACK floods. The objective of this project is to address the existing disparity by curating a compilation of assault approaches that are underutilized. This dataset provides IDS developers with the necessary resources to enhance their detection rates. This research work enhances the security of IoT devices against DDoS botnet assaults, hence contributing to the overall safety of the IoT ecosystem.