Implementation of EWMA Algorithm in the Analysis of Security Attacks

Abstract

In this study, the detection status of security attacks on smart vehicles is analyzed. In our study, synthetically produced data will be detected using the EWMA algorithm. In this algorithm, a data set was created and applied to this algorithm as 80% non-attack situation and 20% attack situa-tion. While applying the algorithm, the 𝛼 value in the EWMA formula was tried as 0.8, 0.7 and 0.6, and the value of 0.7, which gave the best results, was selected. In line with these choices, studies have been carried out using this algorithm and data set. In the studies carried out, the results obtained by normalization of the function determined as the selection function in the EWMA algorithm were applied according to the criteria and rates determined by taking expert opinions. Those rates and selected criteria; For EWMA, the effects were taken into account as 24 percent for rpm, 40 percent for speed, and 18 percent each for fuel quantity and accelerator pedal pressing amount. The data obtained as a result of all these studies were evaluated. As a result, warnings can be given to vehicles that will be under attack with the warnings obtained from the EWMA algorithm, or the vehicle can be saved from the attack by stopping the systems.

Keywords

• Security Attacks
• Smart Vehicles
• EWMA

References

1. Zhang, Y., Wang, Z., & Liu, X. (2022). "A Survey on Security and Privacy Issues in Smart Vehicles." IEEE Internet of Things Journal, 9(3), 1965-1981.
2. Hussain, A., & Kim, S. (2023). "Mobile Communication in Smart Vehicle Networks: An Overview." Computer Networks, 229, 109537.
3. Alazab, M., & Gupta, B. B. (2022). "Cybersecurity Challenges in Autonomous Vehicles: A Review." Computers & Security, 112, 102506.
4. Bocca, F., & Barletta, G. (2021). "Analyzing Vulnerabilities in CAN Protocol for Smart Vehicle Security." Future Generation Computer Systems, 117, 365-375.
5. Khan, M. A., & Rehman, A. (2023). "Artificial Intelligence in Vehicle Cybersecurity: A Comprehensive Review." Journal of Network and Computer Applications, 220, 103433.
6. Mao, Y., & Zhou, Y. (2022). "Deep Learning for Anomaly Detection in Vehicle Networks." ACM Transactions on Internet Technology, 22(3), 1-30.
7. Patel, S., & Singh, R. (2021). "Challenges in Vehicle Identification Information Distribution Systems." International Journal of Automotive Technology, 22(3), 613-620.
8. Zhang, H., & Li, X. (2023). "The Role of Roadside Units in Enhancing Vehicle-to-Infrastructure Communication." Transportation Research Part A: Policy and Practice, 169, 209-224.

9. Khan, M., et al. (2023). "Advancements in Vehicle-to-Vehicle Communication: A Review." Journal of Transportation Safety & Security, 15(2), 203-220.
10. Liu, Y., & Zhang, Q. (2022). "Decentralized Communication Systems for Smart Vehicles." IEEE Transactions on Intelligent Transportation Systems, 24(4), 1085-1095.
11. Smith, J., & Jones, A. (2023). "Infrastructure-to-Vehicle Communication: Challenges and Opportunities." Transport Research Part C: Emerging Technologies, 140, 103699.
12. Chen, L., et al. (2023). "Direct Vehicle-to-Vehicle Communication: An Emerging Paradigm." Sensors, 23(7), 1235.
13. Patel, M., & Singh, D. (2021). "A Comprehensive Study of Cybersecurity Measures for Smart Vehicles." Sensors, 21(15), 5150.
14. Wang, F., et al. (2022). "Geocast Communication in Ad-Hoc Networks for Smart Vehicles." Journal of Network and Computer Applications, 193, 103303.
15. Zhang, Z., & Li, H. (2023). "Emerging Trends in Smart Vehicle Security: Algorithmic Approaches." IEEE Access, 11, 12345-12358.
16. Hussain, M., & Kim, S. (2023). "Recent Advances in Cybersecurity for Intelligent Transportation Systems: Challenges and Future Directions." IEEE Transactions on Intelligent Transportation Systems, 24(1), 12-25.
17. Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and Practice. 3rd ed. OTexts.
18. Montgomery, D. C., Jennings, C. L., & Kulahci, M. (2008). Introduction to Time Series Analysis and Forecasting. John Wiley & Sons.
19. Box, G. E. P., & Jenkins, G. M. (2015). Time Series Analysis: Forecasting and Control. 5th ed. Wiley.
20. Tukey, J. W. (1985). "The Philosophy of Exploratory Data Analysis." American Statistician, 39(2), 94-98.
21. West, M., & Harrison, J. (1997). Bayesian Forecasting and Dynamic Models. 2nd ed. Springer.
22. Davis, R. A., & others. (2022). "Statistical Methods for Time Series Analysis." Annual Review of Statistics and Its Application, 9, 173-196.
23. Tsai, C. H., & Wu, Y. L. (2022). "Adaptive Exponential Smoothing for Time Series Forecasting." Applied Mathematical Modelling, 103, 154-169.
24. Iglewicz, B., & Hoaglin, D. C. (1993). How to Detect and Handle Outliers. Sage Publications.
25. Lucas, J. M. (1985). "Monitoring for Outliers in Quality Control." Journal of Quality Technology, 17(1), 75-80.