Intrusion detection in Internet of Things (IoT) environments represents a crucial aspect of keeping interconnected devices, networks, and data secure from unauthorized access and malicious activities. With IoT’s fast growth in applications ranging from smart homes to industry and healthcare, securing these devices became intrinsic due to their resource-limited nature and diverse architectures. This study examines intrusion detection in IoT networks utilizing XGBoost classifier. A novel version of chimp optimization algorithm has been introduced to execute optimization of XGBoost classifier’s hyperparameters to improve classification capabilities of the model for intrusion detection in IoT systems. Extensive comparative analysis was conducted where the suggested approach was compared against several potent optimizers used in the identical setup. Simulation outcomes indicate superior results of the proposed approach, suggesting its great potential in this particular domain.