Smart City Gnosys
Smart city article details
| Title | Leveraging Optimal Deep Learning With Human-Centered Technologies For Intrusion Detection In Secure Sdn-Based Smart City |
|---|---|
| ID_Doc | 35114 |
| Authors | Maghrabi L.A.; Sabir M.F.; Althaqafi T.; Ashary E.B.; Shabanah S.; Abukhodair F.; Ragab M. |
| Year | 2025 |
| Published | Human-centric Computing and Information Sciences, 15 |
| DOI | http://dx.doi.org/10.22967/HCIS.2025.15.041 |
| Abstract | Human-centered technologies can be used to design intelligent smart cities, enabling residents’ quality of life and safety. These technologies highlight user requirements and preferences, assisting continuous interaction with the urban platform. Combining deep learning (DL) into intrusion detection system (IDS) improves its ability to distinguish intricate patterns and identify novel attacks by learning from massive datasets, providing more precise detection in dynamic software-defined networking (SDN) infrastructure. As SDN develops, overcoming security concerns by incorporating advanced technologies such as DL and attentive feature selection becomes crucial for making protective, adaptive, and robust network substructures. Consequently, this research develops an improved zebra optimizer technique with deep learning employed intrusion detection system (IZOADL-IDS) for SDN. The IZOADL-IDS technique aims to accomplish security by detecting intrusions in the SDN atmosphere. In the IZOADL-IDS technique, the linear scaling normalization technique is employed to measure an input data into a uniform format. In addition, the IZOADL-IDS system applies IZOA to select an optimum set of features. The IZOADL-IDS algorithm uses a bidirectional long short-term memory autoencoder (BiLSTM-AE) method for intrusion detection. Finally, the Aquila optimizer based hyperparameter selection process is involved in adjusting the hyperparameters associated to the BiLSTM-AE technique. The performance assessment of the IZOADL-IDS technique can be made on the benchmark IDS database. The comparative study stated that the IZOADL-IDS system exhibits an excellent accuracy outcome of 98.11% compared to the recent method concerning distinct evaluation measures. © (2025), (Korea Information Processing Society). All rights reserved. |
| Author Keywords | Deep Learning; Hyperparameter Selection; Intrusion Detection System; Software-Defined Networking; Zebra Optimization Algorithm |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
47485  | 0.878 | Tawfik A.T.; Abdullah S.H.; Nori A.S.; Rakha M.A. | Sdn-Enabled Intrusion Detection System Using Machine Learning And Neural Network Schemes | Smart Applications of Artificial Intelligence and Big Data (2025) |
| 17979 | 0.875 | Chinnasamy R.; Malliga S.; Sengupta N. | Deep Learning-Driven Intrusion Detection Systems For Smart Cities-A Systematic Study | IET Conference Proceedings, 2022, 26 (2022) |
| 5008 | 0.862 | Shaffi A.S.; Chacko J.V.; Eliyan G.; Balaji S. | A Study On Anomaly-Based Intrusion Detection Systems Employing Supervised Deep Learning Techniques | Proceedings - 2024 8th International Conference on Inventive Systems and Control, ICISC 2024 (2024) |
| 47749 | 0.862 | Elsayed R.A.; Hamada R.A.; Abdalla M.I.; Elsaid S.A. | Securing Iot And Sdn Systems Using Deep-Learning Based Automatic Intrusion Detection | Ain Shams Engineering Journal, 14, 10 (2023) |
| 19842 | 0.86 | Chinnasamy R.; Subramanian M.; Sengupta N. | Devising Network Intrusion Detection System For Smart City With An Ensemble Of Optimization And Deep Learning Techniques | Proceedings: ICMERALDA 2023 - International Conference on Modeling and E-Information Research, Artificial Learning and Digital Applications (2023) |
| 35068 | 0.859 | Alghanmi N.A. | Leveraging Digital Twins With Hybrid Deep Learning Model For Robust Intrusion Detection System In Smart City Environment | Fusion: Practice and Applications, 19, 1 (2025) |
| 11220 | 0.857 | Haritha V.; Kumutha R.; Shobana G.; Sindhuja R.; Srivastava A.; Mary Sundararajan S.C. | Automated Intrusion Detection And Classification Using Binary Metaheuristics With Deep Learning On Smart Cities | International Conference on Sustainable Communication Networks and Application, ICSCNA 2023 - Proceedings (2023) |
| 33347 | 0.857 | Alrayes F.S.; Asiri M.M.; Maashi M.; Salama A.S.; Hamza M.A.; Ibrahim S.S.; Zamani A.S.; Alsaid M.I. | Intrusion Detection Using Chaotic Poor And Rich Optimization With Deep Learning Model For Smart City Environment | Sustainability (Switzerland), 15, 8 (2023) |
| 23626 | 0.856 | Hazman C.; Guezzaz A.; Benkirane S.; Azrour M. | Enhanced Ids With Deep Learning For Iot-Based Smart Cities Security | Tsinghua Science and Technology, 29, 4 (2024) |
| 18077 | 0.855 | Sai Chaitanya Kumar G.; Kiran Kumar R.; Parish Venkata Kumar K.; Raghavendra Sai N.; Brahmaiah M. | Deep Residual Convolutional Neural Network: An Efficient Technique For Intrusion Detection System | Expert Systems with Applications, 238 (2024) |