Journal of Resource Management and Decision Engineering 5 Serial Number 17 2026 07 01 Detection of Attacks in Internet of Things Devices Using an Optimized Ensemble Classification Based on Deep Transfer Learning and the Harris Hawks Algorithm Detection of Attacks in Internet of Things Devices Using an Optimized Ensemble Classification Based on Deep Transfer Learning and the Harris Hawks Algorithm 1 16 10.61838/kman.jrmde.294 EN Journal Article 2025 12 06 <p>With the rapid expansion of the Internet of Things (IoT) and the increasing number of cyberattacks targeting these devices, the use of efficient methods for attack detection has become increasingly important. In this study, a novel approach based on ensemble deep transfer learning optimized by the Harris Hawks Optimization (HHO) algorithm is proposed for detecting attacks in IoT devices. In this method, multiple deep transfer learning models are employed, which are capable of transferring learned knowledge from data in other domains to IoT-related data. Subsequently, the Harris Hawks algorithm is utilized to optimize the model parameters and integrate them into an ensemble classifier. The Edge-IIoTset dataset is used to evaluate the performance of the proposed method. The obtained results indicate that the detection accuracy reaches 99.8%, while the false alarm rate is significantly reduced. These findings demonstrate the high effectiveness of the proposed method in enhancing the security level of IoT devices.</p> <p> </p> https://www.journalrmde.com/index.php/jrmde/article/download/294/269