The growing utilization of Internet of Things (IoT) applications and services has significantly increased interest in IoT. Organizations are now developing a wide range of IoT devices. However, this rapid expansion and widespread use have made IoT systems attractive targets for hackers, leading to cyber-attacks and data theft. Security remains one of the major challenges in IoT. Distributed denial-of-service (DDoS) attacks represent some of the most harmful and challenging cyber threats to counter within IoT ecosystem. Traditional techniques like signature-based, statistical anomaly recognition, etc., perform well only for detection of simple attacks, while machine learning systems excel at recognizing intricate, exceptional attack patterns. This research addresses this issue by proposing an innovative model utilizing machine learning classifiers to identify IoT-based distributed denial-of-service attacks for binary classification. Various machine learning (ML) algorithms, including decision tree (DT), k-nearest neighbor (k-NN), support vector machine (SVM), Naive Bayes (NB), random forest (RF), and AdaBoost, were implemented to develop a model using the realistic IoT traffic dataset BoT-IoT for the purpose of model training. The optimal algorithm was chosen by considering vital parameters like accuracy percentage, recall, precision, and F1-score.