A comparative study of traditional machine learning models and the KNN-KFSC method for optimizing anomaly detection in VANETs

Abstract

In this research, we conducted a comparative analysis of traditional machine learning techniques and the innovative K-nearest neighbors-K-fuzzy subspace clustering (KNN-KFSC) methodology to detect anomalies in vehicular ad hoc network (VANET) infrastructures. Our evaluation included models such as support vector machine (SVM), random forest (RF), logistic regression (LR), and KNN. The KNN-KFSC model demonstrated exceptional performance with an overall accuracy rate of 99% in handling densely contextual data. It consistently exhibited high accuracy, recall, and F1 score metrics, indicating its effectiveness in detecting a broad spectrum of anomalies across various types of attacks in VANETs. In contrast, the RF algorithm achieved an 89% accuracy rate, showcasing competency in specific domains but revealing limitations in others. Both LR and SVM models exhibited identical accuracy rates of 92%. While effective in identifying specific types of attackers, these models showed weaknesses, potentially due to overfitting or inadequate management of dataset complexity. The KNN-KFSC approach emerged as the most promising option for detecting anomalies in software-defined VANETs, evidenced by its superior performance in accuracy and precision. Our findings underscore the necessity of advanced intrusion detection system techniques and highlight the importance of model refinement to address data imbalances and improve anomaly detection in VANET systems.

Keywords

: Intrusion Detection / KNN-KFSC Method / Machine Learning / VANET / Vehicular Communication

References

[1] Almi’Ani, A., Ghazleh, A.A., Al-Rahayfeh, A., & Razaque, A. (2018). Intelligent Intrusion Detection System Using A Clustered Self-organized Map, In: 2018 Fifth International Conference on Software Defined Systems (SDS), Barcelona, Spain.

[2] Al-Rimy, B.A.S., Maarof, M.A., Alazab, M., Alsolami, F., Shaid, S.Z.M., & Ghaleb, F.A. (2020). A pseudo feedback-based annotated TF-IDF technique for dynamic crypto-ransomware pre-encryption boundary delineation and features extraction. IEEE Access, 8, 140586-140598. https://doi.org/10.1109/ACCESS.2020.3012674

[3] Alsarhan, A., Al-Ghuwairi, A.R., Almalkawi, I.T., Alauthman, M., & Al-Dubai, A. (2021). Machine learning-driven optimization for intrusion detection in smart vehicular networks. Wireless Personal Communications, 117(4), 3129-3152. https://doi.org/10.1007/s11277-020-07797-y

[4] Alshammari, A., Zohdy, M.A., Debnath, D., & Corser, G. (2018). Classification approach for intrusion detection in-vehicle systems. Wireless Engineering and Technology, 9(4), 79-94. https://doi.org/10.4236/wet.2018.94007

[5] Bangui, H., Ge, M., & Buhnova, B. (2021). A hybrid data-driven model for intrusion detection in VANET. Procedia Computer Science, 184, 516-523. https://doi.org/10.1016/j.procs.2021.03.065

[6] Chiti, F., Fantacci, R., Gu, Y., & Han, Z. (2017). Content sharing in Internet of Vehicles: two matching-based user-association approaches. Vehicular Communications, 8, 35-44. https://doi.org/10.1016/j.vehcom.2016.11.005

[7] Cohen, I. Outliers Analysis: A Quick Guide to the Different Types of Outliers. Available from: https://towardsdatascience.com/outliers-analysis-a-quick-guide-to-the-different-types-of-outliers-e41de37e6bf6 [Last accessed on 2021 Mar 17].

[8] Ghaleb, F.A., Maarof, M.A., Zainal, A., Saleh Al-Rimy, B.A., Alsaeedi, A., & Boulila, W. (2019). Ensemble-based hybrid context-aware misbehavior detection model for vehicular ad-hoc network. Remote Sensing, 11(23), 2852. https://doi.org/10.3390/rs11232852

[9] Ghaleb, F.A., Maarof, M.A., Zainal, A., Al-Rimy, B.A.S., Saeed, F., & Al-Hadhrami, T. (2019). Hybrid and multifaceted context-aware misbehavior detection model for vehicular ad-hoc network. IEEE Access, 7, 159119-159140. https://doi.org/10.1109/ACCESS.2019.2950805

[10] Gopi, R., & Rajesh, A. (2017). Securing video cloud storage by ERBAC mechanisms in 5g enabled vehicular networks. Cluster Computing, 20(4), 3489-3497. https://doi.org/10.1007/s10586-017-0987-0

[11] Huang, D., Misra, S., Verma, M., & Xue, G. (2011). PACP: An efficient pseudonymous authentication-based conditional privacy protocol for VANETs. IEEE Transactions on Intelligent Transportation Systems, 12(3), 736-746. https://doi.org/10.1109/TITS.2011.2156790

[12] Leys, C., Delacre, M., Mora, Y., Lakens, D., & Ley, C. (2019). How to classify, detect, and manage univariate and multivariate outliers, with emphasis on pre-registration. International Review of Social Psychology, 32. https://doi.org/10.5334/irsp.289

[13] Liang, J., Chen, J., Zhu, Y., & Yu, R. (2019). A novel intrusion detection system for vehicular ad-hoc networks (VANETs) based on differences of traffic flow and position. Applied Soft Computing, 75, 712-727. https://doi.org/10.1016/j.asoc.2018.12.001

[14] Nie, L., Li, Y., & Kong, X. (2018). Spatio-temporal network traffic estimation and anomaly detection based on convolutional neural network in vehicular ad-hoc networks. IEEE Access, 6, 40168-40176. https://doi.org/10.1109/ACCESS.2018.2854842

[15] Parameshwarappa, P., Chen, Z., & Gangopadhyay, A. (2018). Analyzing attack strategies against rule-based Intrusion Detection Systems. In: Proceedings of the Workshop Program of the 19th International Conference on Distributed Computing and Networking, Varanasi. Association for Computing Machinery, New York, United States.

[16] Patel, S.K., & Sonker, A. (2016). Rule-based network intrusion detection system for port scanning with efficient port scan detection rules using snort. International Journal of Future Generation Communication and Networking, 9(6), 339-350. https://doi.org/10.14257/ijfgcn.2016.9.6.32

[17] Ravikumar, C., Batra, I., & Malik, A. (2022). A comparative analysis on blockchain technology considering security breaches. Lecture Notes in Networks and Systems, 376, 555-565. https://doi.org/10.1007/978-981-16-8826-3_48

[18] Ravikumar, C., Batra, I., & Malik, A. (2021). Combining Blockchain Multi Authority and Botnet to Create a Hybrid Adaptive Crypto Cloud Framework. In: Proceedings of the 2021 International Conference on Computing Sciences (ICCS 2021), pp. 101-106.

[19] Salo, F., Injadat, M., Nassif, A.B., Shami, A., & Essex, A. (2018). Data mining techniques in intrusion detection systems: A systematic literature review. IEEE Access, 6, 56046-56058. https://doi.org/10.1109/ACCESS.2018.2872784

[20] Shams, E.A., Rizaner, A., & Ulusoy, H.A. (2018). Trust aware support vector machine intrusion detection and prevention system in vehicular ad-hoc networks. Computers and Security, 78, 245-254.

[21] Tayyaba, S.K., Khattak, H.A., Almogren, A., Ud Din, I., & Guizani, M. (2020). 5G vehicular network resource management for improving radio access through machine learning. IEEE Access, 8, 6792-6800. https://doi.org/10.1109/ACCESS.2020.2964697

[22] Vitalkar, R.S., Thorat, S.S., & Rojatkar, D.V. (2022). Intrusion Detection For Vehicular ad-hoc Network Based on Deep Belief Network, In: S. Smys, R. Bestak, R. Palanisamy, and I. Kotuliak, Eds., Computer Networks and Inventive Communication Technologies. vol. 75 of Lecture Notes on Data Engineering and Communications Technologies, Springer, Singapore.

[23] Zafar, F., Khattak, H.A., Aloqaily, M., & Hussain, R. (2022). Carpooling in connected and autonomous vehicles: Current solutions and future directions. ACM Computing Surveys, 54(10s), 1-36. https://doi.org/10.1145/3501295

[24] Zeng, Y., Qiu, M., Ming, Z., & Liu, M. (2018). Senior2Local:A machine learning based intrusion detection method for VANETs, In: M. Qiu, Ed., Smart Computing and Communication. vol. 11344 of Lecture Notes in Computer Science, Springer, Cham.

[25] Zhou, M., Han, L., Lu, H., & Fu, C. (2020). Distributed collaborative intrusion detection system for vehicular ad-hoc networks based on invariant. Computer Networks, 172, 107174.