مرکز منطقه ای اطلاع رسانی علوم و فناوری Journal of Information Systems and Telecommunication (JIST) 2322-1437 13 50 2025 7 26 Designing a Hybrid Algorithm that Combines Deep Learning and PSO for Proactive Detection of Attacks in IoT Networks Designing a Hybrid Algorithm that Combines Deep Learning and PSO for Proactive Detection of Attacks in IoT Networks 130 138 10.61882/jist.48455.13.50.130 en Zahra Bakhshali Science and Research Branch, Islamic Azad University, Tehran, Iran. Alireza Pourebrahimi Karaj Branch, Islamic Azad University, Alborz, Iran. Ahmad Ebrahimi Science and Research Branch, Islamic Azad University, Tehran, Iran Nazanin Pilevari west Tehran branch , Islamic Azad University, Tehran, Iran. 2024 11 2 <p>As a result, with the establishment of Internet of Things (IoT) at a booming&ensp;pace, the demand for effective, green security systems to detect cyber-attacks is escalating. Despite thorough investigation in this domain, the heterogeneous nature and multifaceted&ensp;characteristic of IoT data make successful attack detection a challenging task. This paper introduces a new method&ensp;for enhancing IoT attack detection through a hybrid deep learning model (CNN-GRU-LSTM) integrated with Particle Swarm Optimization (PSO) for hyperparameter optimization. This methodology consists of different steps, starting with a&ensp;CSV (Comma Separated Values) file to use it as the dataset, performing different data science operations like feature selection, calculating weights to balance the class for learning the model, etc. A hybrid CNN-GRU-LSTM model is subsequently established and trained with the integration of the merit of each algorithm: CNN for spatial feature abstraction, GRU for effectiveness in managing&ensp;the sequential information, and LSTM for discovering the long-range dependencies. The hyperparameters of the PSO algorithm are optimized to find the best combination&ensp;of features/parameters to improve detection performance and efficiency. &nbsp;The results show remarkable accuracy and efficiency improvements over&ensp;traditional methods. H. PSO for Optimizing Hybrid Deep Learning Architecture The gainful approach&ensp;to building deep neural networks for IoT frameworks is through PSO based improvements. The results help to advance a realm of research work in IoT security and&ensp;lay a grouped foundation for further work in optimizing attack detection models with different machine learning algorithms and optimization approaches.</p> http://jist.ir/en/Article/Download/48455