A Framework for Detection and Comprehensive Review of IoT Botnet Techniques

Abstract

IoT devices have basic security flaws that make them susceptible to a variety of security threats and attacks, including botnet attacks. As a result, botnet developers keep using the security holes in IoT devices to obtain control of multiple host devices on networks and launch cyberattacks against the systems they plan to target. Finding IoT bot vulnerabilities is challenging since methods to get around detection and security measures are constantly being developed. The conceptual frameworks of IoT botnet attacks and different machine-learning-based botnet detection techniques will be looked at in this study. In this article, various botnet detection techniques are reviewed and compared on realistic IoT dataset that covers cutting-edge IoT botnet attack scenarios. The experiments and evaluations unequivocally demonstrate the effectiveness of our approach in detecting botnet activity while minimizing false positives. This research makes a significant contribution to improving IoT security by presenting a robust and scalable solution for detecting botnet attacks, with far-reaching implications for safeguarding critical infrastructure and upholding user privacy. Moving forward, our focus will be on addressing any remaining challenges and validating the practical utility and effectiveness of our methodology in real-world IoT deployments.