F-LTDM: Federated Lightweight Threat Detection Model for Smart City IoT Devices
DOI:
https://doi.org/10.46610/IJMCSE.2025.v01i02.005Keywords:
Anomaly and signature-based detection, Edge computing, Federated learning, Intrusion detection system, Lightweight threat detection, Smart city IoT securityAbstract
Smart city infrastructures rely on large networks of heterogeneous and resource constrained IoT devices, making them increasingly vulnerable to evolving cyber threats. Traditional intrusion detection systems, particularly centralized and deep learning models, struggle to operate effectively in such environments due to high computational demands, privacy concerns, and communication overhead. To address these limitations, this study proposes a Federated Lightweight Threat Detection Model (F- LTDM) that integrates lightweight anomaly detection, signature-based threat identification, and efficient federated learning. The model enables IoT devices to train locally and share only model parameters, preserving data privacy while reducing bandwidth consumption. A communication optimization layer employs gradient sparsification and compressed updates to ensure suitability for low power devices. Experimental evaluation using simulated smart city traffic demonstrates that F-LTDM achieves 96% detection accuracy with a 4% false positive rate, outperforming baseline models such as FedAvg IDS, DeepFed CNN, and DP FL IDS. Results also show significantly lower computational cost (12 ms) and reduced communication overhead (30 MB), confirming the model’s efficiency in real time deployments. Overall, F-LTDM delivers a practical, scalable, and privacy preserving intrusion detection solution tailored to the operational constraints of smart city IoT ecosystems, offering a stronger balance of accuracy, lightweight design, and communication efficiency than existing federated security frameworks.
References
S. Saleem, S. Ashraf, and M. K Basit, “Cmba - A Candid Multi-Purpose Biometric Approach,” ICTACT Journal on Image and Video Processing, vol. 11, no. 1, pp. 2211–2216, Aug. 2020, doi: https://doi.org/10.21917/ijivp.2020.0317
S. Ashraf, M. Gao, Z. Chen, H. Naeem, and T. Ahmed, “CED-OR Based Opportunistic Routing Mechanism for Underwater Wireless Sensor Networks,” Wireless Personal Communications, vol. 125, no. 1, pp. 487–511, Mar. 2022, doi: https://doi.org/10.1007/s11277-022-09561-w
S. Ashraf, S. Saleem, T. Ahmed, and Z. A. Arfeen, “Succulent link selection strategy for underwater sensor network,” International Journal of Computing Science and Mathematics, vol. 15, no. 3, p. 224, 2022, doi: https://doi.org/10.1504/ijcsm.2022.124685
A. Shahzad, “Towards Shrewd Object Visualization Mechanism,” Trends in Computer Science and Information Technology, pp. 097-102, Nov. 2020, doi: https://doi.org/10.17352/tcsit.000030
S. Ashraf, S. Saleem, and S. Afnan, “FTMCP: Fuzzy based Test Metrics for Cosmetology Paradigm,” Advanced Computational Intelligence an International Journal (ACII), vol. 7, no. 4, pp. 1–13, Oct. 2020, doi: https://doi.org/10.5121/acii.2020.7401
S. Ashraf and Z. Aslam, “Data leakage analysis in wireless networks using Supervised and Unsupervised Testing,” Innovación y Software, vol. 4, no. 2, pp. 52–62, Sep. 2023, doi: https://doi.org/10.48168/innosoft.s12.a108
S. Ashraf, Z. A. Arfeen, M. A. Khan, and T. Ahmed, “SLM-OJ: Surrogate Learning Mechanism during Outbreak Juncture,” International Journal for Modern Trends in Science and Technology, vol. 6, no. 5, pp. 162–167, May 2020, doi: https://doi.org/10.46501/ijmtst060525
J. Mills, J. Hu, and G. Min, “Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoT,” IEEE Internet of Things Journal, vol. 28, no. 7, pp. 1–1, 2019, doi: https://doi.org/10.1109/jiot.2019.2956615
F. Mosaiyebzadeh et al., “Privacy-Preserving Federated Learning-Based Intrusion Detection System for IoHT Devices,” Electronics, vol. 14, no. 1, pp. 67–67, Dec. 2024, doi: https://doi.org/10.3390/electronics14010067
S. Ashraf, A. Ahmad, A. Yahya, and T. Ahmed, “Underwater routing protocols: Analysis of link selection challenges,” AIMS Electronics and Electrical Engineering, vol. 4, no. 3, pp. 234–248, 2020, doi: https://doi.org/10.3934/electreng.2020.3.234
Z. Rasheed, S. Ashraf, N. A. Ibupoto, P. K. Butt, and E. H. Sadiq, “SDS: Scrumptious Dataflow Strategy for IoT Devices in Heterogeneous Network Environment,” Smart Cities, vol. 5, no. 3, pp. 1115–1128, Sep. 2022, doi: https://doi.org/10.3390/smartcities5030056
S. Ashraf, S. Saleem, and T. Ahmed, “Sagacious Communication Link Selection Mechanism for Underwater Wireless Sensors Network,” International Journal of Wireless and Microwave Technologies, vol. 10, no. 4, pp. 22–33, Aug. 2020, doi: https://doi.org/10.5815/ijwmt.2020.04.03
S. Ashraf, “Avoiding Vulnerabilities and Attacks with a Proactive Strategy for Web Applications,” Advances in Robotics & Mechanical Engineering, vol. 3, no. 2, Aug. 2021, doi: https://doi.org/10.32474/arme.2021.03.000157
S. Ashraf, D. Muhammad, and M. A. Khan, “AI-Driven Customer Relationship Management: Enhancing Salesforce Efficiency Through Predictive Analytics,” International Journal of Advance Industrial Engineering, vol. 13, no. 01, pp. 22–35, 2025, doi: https://doi.org/10.14741/
M. Z. Zuhair, S. Ashraf, M. Iqbal, and A. Khokhar, “Broaching Uncouth Water Level Snag in Underground Agriculture Field Through Wireless Sensors,” Suranaree Journal of Science and Technology, vol. 30, no. 4, pp. 010248(1-16), Oct. 2023, doi: https://doi.org/10.55766/sujst-2023-04-e0855.
A. Shahzad and A. Tauqeer, “Dual-nature biometric recognition epitome,” Trends in Computer Science and Information Technology, vol. 5, no. 1, pp. 008-014, Jun. 2020, doi: https://doi.org/10.17352/tcsit.000012
S. Ashraf, Z. Aslam, S. Saleem, S. Afnan, and M. Aamer, “Multi-biometric Sustainable Approach for Human Appellative,” Computational Research Progress in Applied Science and Engineering, vol. 6, no. 3, pp. 146–152, 2020, Accessed: Nov. 28, 2025. [Online]. Available: https://www.htpub.org/article/Computational-Research-Progress-In-Applied-Science-And-Engineering/vol/6/issue/3/articleid/841
S. Ashraf, F. Memon, F. Akram, T. A. Siddique, and Y. Aziz, “Modeling wireless sensors network using shrewd neural networks,” Blockchain and Digital Twin for Smart Healthcare, pp. 373–393, 2025, doi: https://doi.org/10.1016/b978-0-443-30300-5.00021-x
S. Ashraf, F. Memon, F. Akram, Z. Rasheed, S. S. Bhatti, and I. Ullah, “Development of Sustainable Wireless Resource model through Shrewd Neural Network,” Data Intelligence, vol. 6, no. 3, pp. 649–665, Aug. 2024, doi: https://doi.org/10.3724/2096-7004.di.2024.0034
A. Shahzad, R. Zeeshan, and A. Muhammad, “Adopting proactive results by developing the Shrewd model of pandemic COVID-19,” Archives of Community Medicine and Public Health, vol. 8, no. 2, pp. 062–067, Apr. 2022, doi: https://doi.org/10.17352/2455-5479.000175
S. Ashraf, Z. Aslam, S. Saleem, S. Afnan, and M. Aamer, “Multi-biometric Sustainable Approach for Human Appellative,” Computational Research Progress in Applied Science and Engineering, vol. 6, no. 3, pp. 146–152, 2020, Available: https://www.htpub.org/article/Computational-Research-Progress-In-Applied-Science-And-Engineering/vol/6/issue/3/articleid/841
A. Karunamurthy, K. Vijayan, P. R. Kshirsagar, and K. T. Tan, “An optimal federated learning-based intrusion detection for IoT environment,” Scientific Reports, vol. 15, no. 1, Mar. 2025, doi: https://doi.org/10.1038/s41598-025-93501-8
