Indonesian Journal of Electrical Engineering and Computer Science Vol. 38, No. 3, June 2025, pp. 1804~1818 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v38.i3.pp1804-1818  1804 Journal homepage: http://ijeecs.iaescore.com IoT based intrusion detection data analysis using deep learning models Marwa Baich, Nawal Sael, Touria Hamim Laboratory of Information Technology and Modeling, Faculty of Sciences, Ben M’Sik, Hassan II University of Casablanca, Casablanca, Morocco Article Info ABSTRACT Article history: Received May 17, 2024 Revised Nov 20, 2024 Accepted Nov 30, 2024 In both the academic and industrial domains, integration of the internet of things (IoT) is now universally accepted as a significant technical achievement. IoT offers a multitude of security issues despite its many advantages, such as protecting networks and devices, handling resource- constrained network scenarios, and controlling threats to IoT networks. This article gives a state-of-the-art analysis on the application of multiple deep learning (DL) algorithms in IoT intrusion detection systems (IDS), covering the years 2020 to 2024. Moreover, two popular network datasets, NSL-KDD and UNSW-NB15, are used for an experimental evaluation. The study thoroughly examines and assesses the advantages of well-known deep learning algorithms, including DNN, CNN, RNN, LSTM, and FFDNN. The study demonstrates the exceptional performance of the DNN approach on both datasets, with 99.14% accuracy in multiclass classification in NSL- KDD and 99.36% accuracy in binary classification. Furthermore, on UNSW- NB15, 82.26% of multiclass classifications and 93.96% of binary classifications with a 42-second minimum running time were achieved, along with an excellent performance in reducing false alarms at a rate of 2.19%. Keywords: Cybersecurity Deep learning Internet of things Intrusion detection system UNSW-NB15 NSL-KDD This is an open access article under the CC BY-SA license. Corresponding Author: Marwa Baich Laboratory of Information Technology and Modeling, Faculty of Sciences Ben M’Sik, Hassan II University of Casablanca Casablanca, Morocco Email: marwa.baich-etu@etu.univh2c.ma 1. INTRODUCTION The smart devices are becoming more and more commonplace in many daily activities due to the increasing prevalence of technology improvements in sensors, automatic item recognition, tracking, communication among interconnected devices, and integrated Internet services. Studies conducted by Cisco predict that the Internet of Things, it is projected that there will be approximately 75.3 billion devices that are actively linked by 2025 [1]. IoT technology differs from conventional Internet technologies in that it has the ability to facilitate data sharing across systems without requiring human intervention. Acknowledging the crucial significance of cybersecurity becomes essential, especially as the IoT takes center stage as the driving force behind the ongoing industrial revolution and serves as the primary infrastructure for collecting real-time data [2]. It needs to be underlined that IoT-based intrusion detection research is extremely indispensable for enhancing security and privacy in such dynamic and networked environments. This will also provide the base for novel solutions and adaptive approaches toward effectively combating emerging threats and securing IoT networks. Installing a network intrusion detection system (NIDS) that can recognize both active and future assaults is essential for safeguarding the IoT network and the systems that are developed on it. When a breach is detected, an IDS can monitor the network activities