Among all IoT applications, the smart home is the most treasured use case. Smart home set-ups seem like luxury requisites, but, nowadays, they have become indispensable for those leading busy lives. People have started thinking that being connected to home appliances 24 × 7 is not a style quotient but a safety measure. The major concern regarding smart homes is their security issues because they are based on IoT, which works on constrained resources and is therefore extremely prone to several types of attacks. As the use of IoT is increasing, attackers are developing highly powerful attack tools. However, research and development in the fields of ML, DL, and AI have contributed to rigid and robust security mechanisms. The urgent need of the hour is to apply ML techniques to safeguard IoT-based applications and establish effective security models. In this paper, we aim to design an ML-driven security model to predict DDoS attacks within IoT-enabled smart home networks. Our study evaluates the accuracy of different machine learning algorithms, including Artificial Neural Networks (ANN), decision trees, random forest, naive Bayes, and Support Vector Machines (SVM), in detecting DDoS attacks targeted at smart homes. We utilized the BoT_IoT 2018 dataset, which was developed at the Cyber Range Lab of the University of New South Wales, Canberra, Australia.