Open Access
Research Article
Hybrid deep learning-based IoT intrusion detection : A comparative study of CNN, GRU, LSTM, and hybrid architectures
*Sonkarlay J.Y. WeamieCorresponding authorskweamie@hnu.edu.cnCollege of Computer Science and Electronic Engineering Hunan University Yuelu DistrictChangsha, Hunan, 410082, China0000-0002-9414-7171View full profile → , Vinothkumar Kolluruvkolluru@stevens.eduDepartment of Data Science Stevens Institute of Technology 1 Castle Point TerraceHoboken, NJ, 07030, U.S.A.0009-0006-1713-5720View full profile → , AB Jallah Balyemah AB Jallah Balyemahab.jallah1990@gmail.comCollege of Computer Science and Electronic Engineering Hunan University Yuelu DistrictChangsha, Hunan, 410082, China0009-0002-8815-6060View full profile → , Yagnesh Challagundlayagneshnaidu1234@gmail.comDepartment of Engineering Education Herbert Wertheim College of Engineering University of FloridaDepartment of Engineering Education Herbert Wertheim College of Engineering University of FloridaGainesville, Florida, 32611, U.S.A.0009-0005-5221-1517View full profile →
* Corresponding author · click or hover a name for details
- Received:
- 10 Dec 2024
- Published Online:
- 01 Sep 2025
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2027
- Pages:
- 1983–1994
Abstract
Cyber-physical systems, particularly Internet of Things devices, pose significant cybersecurity challenges due to their vast volume, speed, and complexity of network traffic and attack vectors. This research presents an innovative hybrid deep learning technique to improve intrusion detection by taking full advantage of spatial and temporal characteristics from IoT network traffic. In this paper, we conduct a systematic study to compare different deep learning models, including CNN, GRUs, and LSTM networks, as well as their hybrid architectures such as CNN- GRU and CNN-LSTM on real-world NB-IoT dataset with benign traffic traces mixed up against targeted attacks from Mirai/Gafgyt botnets. The CNN-LSTM hybrid model demonstrated significant performance in IoT intrusion detection, achieving accuracy rates of 94.7%, precision of 94.6%, recall of 94.7%, and F1-score of 94.6%.
Keywords
Subject Classifications
68T0768T4568M10
References
[1] T. K. Mohammed, D. N. Vasundhara, S. H. Mehanoor, E. Sreedevi, P. R. Kumar, C. Manihass, and S. F. Baba, “A novel fusion approach for advancement in crime prediction and forecasting using hybridization of ARIMA and recurrent neural networks,” Journal of Information Systems Engineering and Management, vol. 10, no. 38, pp. 404–420 (2025).[2] B. Shilpa, P. R. Kumar, and R. K. Jha, “LoRa DL: A deep learning model for enhancing the data transmission over LoRa using autoencoder,” The Journal of Supercomputing, vol. 79, no. 15, pp. 17079–17097 (2023).[3] R. Q. Abdulkadhim, H. S. Abdullah, and M. J. Hadi, “Improving cryptocurrency price prediction through advanced LSTM-based deep learning techniques,” Journal of Statistics and Management Systems, vol. 27, no. 8, pp. 1701–1712 (2024).[4] V. Kantharaju, H. Suresh, M. N., S. Ansarullah, F. Amin, and A. Alabrah, “Machine learning based intrusion detection framework for detecting security attacks in internet of things,” Scientific Reports, vol. 14 (2024).[5] J.-M. Chen, “Multi-vendor and multi-buyer collaborative planning, forecasting and replenishment model,” Journal of Statistics and Management Systems, vol. 28, no. 6, pp. 1023–1036 (2025).[6] P. R. Kumar and B. Shilpa, “An IoT-based smart healthcare system with edge intelligence computing,” in Reconnoitering the landscape of edge intelligence in healthcare, pp. 31–46, Apple Academic Press (2024).[7] M. R. Z. E. Deen and G. M. Elmahdy, “Different types of odd harmonious labeling of super subdivision of various graphs,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 8, pp. 2373–2407 (2024).[8] B. Cao, C. Li, Y. Song, and X. Fan, “Network intrusion detection technology based on convolutional neural network and BiGRU,” Computational Intelligence and Neuroscience (2022).[9] R. Ranjan, D. Pandey, A. K. Rai, D. Gupta, P. Singh, P. R. Kumar, and S. N. Mohanty, “A manifold-level hybrid deep learning approach for sentiment classification using an autoregressive model,” Applied Sciences, vol. 13, no. 5, pp. 3091 (2023).[10] N. Thilakarathne, G. Muneeswari, P. V., F. Alassery, H. Hamam, R. Mahendran, et al., “Federated learning for privacy-preserved medical Internet of Things,” Intelligent Automation & Soft Computing, vol. 33, pp. 157–172 (2022).[11] B. Shilpa, P. R. Kumar, and R. K. Jha, “Spreading factor optimization for interference mitigation in dense indoor LoRa networks,” in 2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET), pp. 1–5 (2023).[12] G. Zhao, C. Ren, J. Wang, Y. Huang, and H. Chen, “IoT intrusion detection model based on gated recurrent unit and residual network,” Peer-to-Peer Networking and Applications, vol. 16, pp. 1–13 (2023).[13] I. Mani, Naveen, Anjana, and R. Bhardwaj, “Common fixed-point theorems satisfying rational contraction in partially ordered metric space,” Journal of Interdisciplinary Mathematics, vol. 27, no. 8, pp. 1773–1779 (2024).[14] Z. Al-Khuzaie, S. Albermany, and M. AbdlNibe, “Intrusion detection in the IoT-Fog adopting the GRU and CNN: A deep learning-based approach,” pp. 379–389 (2023).[15] P. R. Kumar and T. Ananthan, “Machine vision using LabVIEW for label inspection,” Journal of Innovation in Computer Science and Engineering, vol. 9, no. 1, pp. 58–62 (2019).[16] R. Q. Abdulkadhim, H. S. Abdullah, and M. J. Hadi, “Improving cryptocurrency price prediction through advanced LSTM-based deep learning techniques,” Journal of Statistics and Management Systems, vol. 27, no. 8, pp. 1701–1712 (2024).
Views: 181Downloads: 12Citations: 1
