Smart City Gnosys
Smart city article details
| Title | Can Machine Learning Enhance Intrusion Detection To Safeguard Smart City Networks From Multi-Step Cyberattacks? |
|---|---|
| ID_Doc | 13293 |
| Authors | Khan J.; Elfakharany R.; Saleem H.; Pathan M.; Shahzad E.; Dhou S.; Aloul F. |
| Year | 2025 |
| Published | Smart Cities, 8, 1 |
| DOI | http://dx.doi.org/10.3390/smartcities8010013 |
| Abstract | Highlights: What are the main findings? Using machine learning was found to be effective in identifying and classifying multi-step network intrusion cyberattacks. Extreme Gradient Boosting (XGB) was identified as the top-performing machine learning model due to its high accuracy and computational efficiency, making it an ideal choice for an edge-based intrusion detection system (IDS). What is the implication of the main finding? Identifying and classifying multi-step cyberattacks through advanced IDS help protect smart cities’ systems from unauthorized access, ensuring the stability, security, and reliability of essential services. Given the dynamic nature of smart cities, where multiple systems work in tandem and data flow in real-time, this research highlights the importance of developing real-time intrusion detection systems that are able to detect intrusions as soon as they arise, enabling quick actions to isolate and mitigate risks before they can cause widespread damage. Intrusion detection systems are essential for detecting network cyberattacks. As the sophistication of cyberattacks increases, it is critical that defense technologies adapt to counter them. Multi-step attacks, which need several correlated intrusion operations to reach the desired target, are a rising trend in the cybersecurity field. System administrators are responsible for recreating whole attack scenarios and developing improved intrusion detection systems since the systems at present are still designed to generate alerts for only single attacks with little to no correlation. This paper proposes a machine learning approach to identify and classify multi-step network intrusion attacks, with particular relevance to smart cities, where interconnected systems are highly vulnerable to cyber threats. Smart cities rely on these systems seamlessly functioning with one another, and any successful cyberattack could have devastating effects, including large-scale data theft. In such a context, the proposed machine learning model offers a robust solution for detecting and mitigating multi-step cyberattacks in these critical environments. Several machine learning algorithms are considered, namely Decision Tree (DT), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machine (SVM), Light Gradient-Boosting Machine (LGBM), Extreme Gradient Boosting (XGB) and Random Forest (RF). These models are trained on the Multi-Step Cyber-Attack Dataset (MSCAD), a recent dataset that is highly representative of real-world multi-step cyberattack scenarios, which increases the accuracy and efficiency of such systems. The experimental results show that the best performing model was XGB, which achieved a testing accuracy of 100% and an F1 Score of 88%. The proposed model is computationally efficient and easy to deploy, which ensures a fast, sustainable and low power-consuming intrusion detection system at the cutting edge. © 2025 by the authors. |
| Author Keywords | cyberattack; cybersecurity; deep learning; intrusion detection; machine learning |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
2187  | 0.923 | Gill K.S.; Dhillon A. | A Hybrid Machine Learning Framework For Intrusion Detection System In Smart Cities | Evolving Systems, 15, 6 (2024) |
| 19240 | 0.915 | Rangani H.; Chandrashekar K. | Detection And Prevention Of Cyber Threats In Smart Cities Using Machine Learning And Intrusion Detection Systems | 2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024 - Proceedings (2024) |
| 814 | 0.911 | Basheer L.; Ranjana P. | A Comparative Study Of Various Intrusion Detections In Smart Cities Using Machine Learning | 2022 International Conference on IoT and Blockchain Technology, ICIBT 2022 (2022) |
| 17029 | 0.905 | Protic D.; Gaur L.; Stankovic M.; Rahman M.A. | Cybersecurity In Smart Cities: Detection Of Opposing Decisions On Anomalies In The Computer Network Behavior | Electronics (Switzerland), 11, 22 (2022) |
| 2481 | 0.903 | Gore S.; Deshpande A.S.; Mahankale N.; Singha S.; Lokhande D.B. | A Machine Learning-Based Detection Of Iot Cyberattacks In Smart City Application | Lecture Notes in Networks and Systems, 782 LNNS (2023) |
| 23834 | 0.896 | Al-Atawi A.A. | Enhancing Internet Of Smart City Security: Utilizing Logistic Boosted Algorithms For Anomaly Detection And Cyberattack Prevention | SN Computer Science, 5, 5 (2024) |
| 24715 | 0.896 | Ali M.; Pervez S.; Hosseini S.E.; Siddhu M.K. | Evaluation And Detection Of Cyberattack In Iot-Based Smart City Networks Using Machine Learning On The Unsw-Nb15 Dataset | International Journal of Online and Biomedical Engineering, 21, 2 (2025) |
| 1446 | 0.893 | Rakha M.A.; Akbar A.; Chhabra G.; Kaushik K.; Arshi O.; Khan I.U. | A Detailed Comparative Study Of Ai-Based Intrusion Detection System For Smart Cities | Proceedings of International Conference on Communication, Computer Sciences and Engineering, IC3SE 2024 (2024) |
| 57650 | 0.89 | Hazman C.; Guezzaz A.; Benkirane S.; Azrour M. | Toward An Intrusion Detection Model For Iot-Based Smart Environments | Multimedia Tools and Applications, 83, 22 (2024) |
| 6993 | 0.89 | Alhamdi M.J.M.; Lopez-Guede J.M.; AlQaryouti J.; Rahebi J.; Zulueta E.; Fernandez-Gamiz U. | Ai-Based Malware Detection In Iot Networks Within Smart Cities: A Survey | Computer Communications, 233 (2025) |