Smart City Gnosys
Smart city article details
| Title | Ai-Driven Ensemble Classifier For Jamming Attack Detection In Vanets To Enhance Security In Smart Cities |
|---|---|
| ID_Doc | 7023 |
| Authors | El-Shafai W.; Azar A.T.; Ahmed S. |
| Year | 2025 |
| Published | IEEE Access, 13 |
| DOI | http://dx.doi.org/10.1109/ACCESS.2025.3552544 |
| Abstract | Vehicular Ad-hoc Networks (VANETs) are integral to the fabric of Intelligent Transportation Systems (ITSs), facilitating essential vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. However, the rising prevalence of jamming attacks, characterized by the intentional disruption of communications through interference signals, presents a significant challenge to the security of VANETs and, consequently, public safety. This emerging threat highlights a critical research gap in the development of sophisticated, AI-driven security solutions for VANETs. In response to this challenge, our study introduces an innovative artificial intelligence (AI) model, meticulously engineered to detect jamming attacks in VANETs. This model represents a synergistic integration of an array of machine learning (ML) and deep learning (DL) classifiers, meticulously analyzing signal characteristics within VANET communication channels. Its primary aim is the effective identification of anomalous patterns signaling the presence of jamming attacks. Extensive simulations were conducted to rigorously test the model's efficacy, which yielded encouraging results. Initially, we assessed the detection accuracy of 14 different ML classifiers and 4 DL classifiers. Subsequently, we proposed a voting-based ensemble AI classifier combining the most accurate ML and DL classifiers, namely Random Forest (RF), Extra Tree (ET), and fine-tuned Convolutional Neural Network (CNN). This ensemble classifier, RF+ET+CNN, achieved the highest detection accuracy, outperforming the individual classifiers. Specifically, the CNN algorithm demonstrated an exceptional detection accuracy of 99.133%, while the RF and ET classifiers were the most accurate among the ML algorithms tested, with accuracy rates of 97.4359% and 97.4357%, respectively. Notably, the proposed RF+ET+CNN ensemble classifier achieved an impressive detection accuracy of 99.8125%. These findings underscore the superiority of our proposed model over existing jamming detection models. The integration of this model into existing VANET security systems is anticipated to significantly enhance their capability to mitigate jamming attacks, thereby reinforcing the overall security and reliability of VANET communications. This advancement is particularly pertinent in the context of smart city infrastructures, where the safety and efficiency of transportation networks are paramount. © 2025 IEEE. |
| Author Keywords | artificial intelligence; ensemble learning; jamming attack detection; network security; smart cities; VANET |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
2469  | 0.916 | Rabah N.B.; Idoudi H. | A Machine Learning Framework For Intrusion Detection In Vanet Communications | Emerging Trends in Cybersecurity Applications (2022) |
| 44548 | 0.91 | Bangui H.; Buhnova B. | Recent Advances In Machine-Learning Driven Intrusion Detection In Transportation: Survey | Procedia Computer Science, 184 (2021) |
| 33323 | 0.903 | Arya M.; Sastry H.; Dewangan B.K.; Rahmani M.K.I.; Bhatia S.; Muzaffar A.W.; Bivi M.A. | Intruder Detection In Vanet Data Streams Using Federated Learning For Smart City Environments | Electronics (Switzerland), 12, 4 (2023) |
| 36054 | 0.894 | Masmoudi O.; Idoudi H.; Mosbah M. | Machine Learning-Based Intrusion Detection For Position Falsification Attack In The Internet Of Vehicles | Intelligent Systems for IoE Based Smart Cities (2023) |
| 36079 | 0.887 | Khatua S.; Das S.; Nandi A.; Kumar A.; De D.; Roy S. | Machine Learning-Inspired Intrusion Detection On Vehicular Communication For Route Planning | Lecture Notes in Networks and Systems, 1158 LNNS (2025) |
| 58842 | 0.886 | Aleisa H.N.; Alrowais F.; Allafi R.; Almalki N.S.; Faqih R.; Marzouk R.; Alnfiai M.M.; Motwakel A.; Ibrahim S.S. | Transforming Transportation: Safe And Secure Vehicular Communication And Anomaly Detection With Intelligent Cyber-Physical System And Deep Learning | IEEE Transactions on Consumer Electronics, 70, 1 (2024) |
| 33338 | 0.882 | Ventura H.T.; Moretti R.A.; Vendramin A.C.B.K.; Pigatto D.F. | Intrusion Detection In Vehicular Networks Using Machine Learning | Journal of Internet Services and Applications, 16, 1 (2025) |
| 2508 | 0.881 | Mishra D.; Moudgi S.; Virmani D.; Faniband Y.P.; Nandyal A.B.; Sahu P.K.; Singh G. | A Mathematical Framework For Enhancing Iot Security In Vanets: Optimizing Intrusion Detection Systems Through Machine Learning Algorithms | Communications on Applied Nonlinear Analysis, 31, 8s (2024) |
| 784 | 0.881 | Sepasgozar S.S.; Pierre S. | A Comparative Study Of Artificial Intelligence Algorithms For Network Traffic Prediction In Vanet | International Conference on Wireless and Mobile Computing, Networking and Communications, 2022-October (2022) |
| 53646 | 0.876 | Aloqaily A.; Abdallah E.E.; AbuZaid H.; Abdallah A.E.; Al-hassan M. | Supervised Machine Learning For Real-Time Intrusion Attack Detection In Connected And Autonomous Vehicles: A Security Paradigm Shift | Informatics, 12, 1 (2025) |