{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T01:22:03Z","timestamp":1778203323752,"version":"3.51.4"},"reference-count":27,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Electronics"],"abstract":"<jats:p>This paper proposes a novel AI-driven anomaly detection framework designed to enhance cybersecurity in IoT-enabled smart cities operating over 5G networks. While prior research has explored deep learning for anomaly detection, most existing systems rely on single-model architectures, employ centralized training, or lack support for real-time, privacy-preserving deployment\u2014limiting their scalability and robustness. To address these gaps, our system integrates a hybrid deep learning model combining autoencoders, long short-term memory (LSTM) networks, and convolutional neural networks (CNNs) to detect spatial, temporal, and reconstruction-based anomalies. Additionally, we implement federated learning and edge AI to enable decentralized, privacy-preserving threat detection across distributed IoT nodes. The system is trained and evaluated using a combination of real-world (CICIDS2017, TON_IoT, UNSW-NB15) and synthetically generated attack data, including adversarial perturbations. Experimental results show our hybrid model achieves a precision of 97.5%, a recall of 96.2%, and an F1 score of 96.8%, significantly outperforming traditional IDS and standalone deep learning methods. These findings validate the framework\u2019s effectiveness and scalability, making it suitable for real-time intrusion detection and autonomous threat mitigation in smart city environments.<\/jats:p>","DOI":"10.3390\/electronics14122492","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T08:43:58Z","timestamp":1750322638000},"page":"2492","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["AI-Driven Anomaly Detection for Securing IoT Devices in 5G-Enabled Smart Cities"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8872-5721","authenticated-orcid":false,"given":"Manuel J. C. S.","family":"Reis","sequence":"first","affiliation":[{"name":"Engineering Department & IEETA, University of Tr\u00e1s-os-Montes e Alto Douro, Quinta de Prados, 5000-801 Vila Real, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Priyadarshini, I. (2024). Anomaly Detection of IoT Cyberattacks in Smart Cities Using Federated Learning and Split Learning. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8030021"},{"key":"ref_2","unstructured":"Institute for Defense & Business (2025, March 17). What Are the Cybersecurity Risks for Smart Cities?. Available online: https:\/\/www.idb.org\/what-are-the-cybersecurity-risks-for-smart-cities\/."},{"key":"ref_3","unstructured":"(2025, March 17). Security and Compliance in 5G and AI-Powered Edge Networks | Deloitte Global. Available online: https:\/\/www.deloitte.com\/global\/en\/services\/consulting-risk\/perspectives\/security-compliance-in-5g-ai-powered-edge-networks.html."},{"key":"ref_4","unstructured":"(2025, March 17). How 5G Technology Affects Cybersecurity: Looking to the Future | UpGuard. Available online: https:\/\/www.upguard.com\/blog\/how-5g-technology-affects-cybersecurity."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100601","DOI":"10.1016\/j.jik.2024.100601","article-title":"Towards a Conceptual Framework for AI-Driven Anomaly Detection in Smart City IoT Networks for Enhanced Cybersecurity","volume":"9","author":"Mirza","year":"2024","journal-title":"J. Innov. Knowl."},{"key":"ref_6","unstructured":"(2025, March 17). Cybersecurity Challenges in Smart Cities: An Overview and Future Prospects | Mesopotamian Journal of CyberSecurity. Available online: https:\/\/mesopotamian.press\/journals\/index.php\/CyberSecurity\/article\/view\/14."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"USA, and Aluwala, A. (2024). AI-Driven Anomaly Detection in Network Monitoring Techniques and Tools. J. Artif. Intell. Cloud Comput., 1\u20136.","DOI":"10.47363\/JAICC\/2024(3)310"},{"key":"ref_8","unstructured":"Babu, C.V.S., and Simon, P.A. (2025, March 17). Adaptive AI for Dynamic Cybersecurity Systems: Enhancing Protection in a Rapidly Evolving Digital Landscap. Available online: https:\/\/www.igi-global.com\/gateway\/chapter\/337688."},{"key":"ref_9","first-page":"1573","article-title":"Adaptive Security Framework For Iot: Utilizing AI And ML To Counteract Evolving Cyber Threats","volume":"29","author":"Kuraku","year":"2023","journal-title":"Educ. Adm. Theory Pract."},{"key":"ref_10","unstructured":"(2025, March 17). What Is the Role of AI in Threat Detection?. Available online: https:\/\/origin-www.paloaltonetworks.com\/cyberpedia\/ai-in-threat-detection."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kuguoglu, B.K., van der Voort, H., and Janssen, M. (2021). The Giant Leap for Smart Cities: Scaling Up Smart City Artificial Intelligence of Things (AIoT) Initiatives. Sustainability, 13.","DOI":"10.3390\/su132112295"},{"key":"ref_12","unstructured":"(2025, March 17). Towards Large-Scale IoT Deployments in Smart Cities: Requirements and Challenges | SpringerLink. Available online: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-50514-0_6."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zyrianoff, I., Borelli, F., Biondi, G., Heideker, A., and Kamienski, C. (2018, January 25\u201328). Scalability of Real-Time IoT-Based Applications for Smart Cities. Proceedings of the 2018 IEEE Symposium on Computers and Communications (ISCC), Natal, Brazil.","DOI":"10.1109\/ISCC.2018.8538451"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"100656","DOI":"10.1016\/j.iot.2022.100656","article-title":"Deep Learning-Enabled Anomaly Detection for IoT Systems","volume":"21","author":"Abusitta","year":"2022","journal-title":"Internet Things"},{"key":"ref_15","unstructured":"(2025, March 17). AI and IoT in Smart Cities Security. Available online: https:\/\/www.truehomeprotection.com\/leveraging-ai-and-iot-for-next-generation-security-systems-in-smart-cities\/."},{"key":"ref_16","first-page":"1687","article-title":"Smart City Infrastructure Monitoring Using AI and IoT Technologies","volume":"12","author":"More","year":"2024","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103299","DOI":"10.1016\/j.cose.2023.103299","article-title":"Clustered Federated Learning Architecture for Network Anomaly Detection in Large Scale Heterogeneous IoT Networks","volume":"131","author":"Flores","year":"2023","journal-title":"Comput. Secur."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/TE.2016.2608779","article-title":"Innovative Mobile Robot Method: Improving the Learning of Programming Languages in Engineering Degrees","volume":"60","author":"Ortiz","year":"2017","journal-title":"IEEE Trans. Educ."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Elshaiekh, N.E.M., Hassan, Y.A.A., and Abdallah, A.A.A. (2018, January 28\u201330). The Impacts of Remote Working on Workers Performance. Proceedings of the 2018 International Arab Conference on Information Technology (ACIT), Sultan Qaboos University, Muscat, Oman.","DOI":"10.1109\/ACIT.2018.8672704"},{"key":"ref_20","first-page":"45","article-title":"AI-Based Anomaly Detection for Real-Time Cybersecurity","volume":"3","author":"Goswami","year":"2024","journal-title":"Int. J. Res. Rev. Tech."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3480172","article-title":"Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach","volume":"3","author":"Ngo","year":"2021","journal-title":"ACM Trans. Internet Things"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"14285","DOI":"10.1109\/JIOT.2023.3243391","article-title":"Unsupervised Deep Learning for IoT Time Series","volume":"10","author":"Liu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4456","DOI":"10.1109\/TNET.2024.3423780","article-title":"Federated PCA on Grassmann Manifold for IoT Anomaly Detection","volume":"32","author":"Nguyen","year":"2024","journal-title":"IEEEACM Trans. Netw."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zolanvari, M., Ghubaish, A., and Jain, R. (2021, January 3\u20135). ADDAI: Anomaly Detection Using Distributed AI. Proceedings of the 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC), Xiamen, China.","DOI":"10.1109\/ICNSC52481.2021.9702157"},{"key":"ref_25","unstructured":"Subasi, O., Cree, J., Manzano, J., and Peterson, E. (2024). A Critical Assessment of Interpretable and Explainable Machine Learning for Intrusion Detection. arXiv."},{"key":"ref_26","unstructured":"Garcia, E. (2025, May 15). Smart City and Iot Data Collection Leveraging Generative Ai. Available online: https:\/\/philpapers.org\/rec\/GARSCA-9."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"61611","DOI":"10.1109\/ACCESS.2025.3555926","article-title":"Explainable Artificial Intelligence (XAI) for Malware Analysis: A Survey of Techniques, Applications, and Open Challenges","volume":"13","author":"Manthena","year":"2025","journal-title":"IEEE Access"}],"container-title":["Electronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-9292\/14\/12\/2492\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:04Z","timestamp":1760032504000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-9292\/14\/12\/2492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":27,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["electronics14122492"],"URL":"https:\/\/doi.org\/10.3390\/electronics14122492","relation":{},"ISSN":["2079-9292"],"issn-type":[{"value":"2079-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,19]]}}}