Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles †
Abstract
:1. Introduction
2. Methodology
2.1. Dataset
2.2. Machine Learning
2.3. Evaluation Metric
3. Results and Discussions
3.1. LED Light Strobe
3.2. Color Lighting
- Signs with r values lower than 0.5 included speed limit 60, speed limit 70, speed limit 80, speed limit 120, no truck overtaking, left bend, uneven road surface, reduced road limit, watch out for snow, watch out for wild animals, and the ban is lifted.
- Signs with p values lower than 0.5 with red overlay included vehicle entry is prohibited, danger, and following the direction.
- Signs with p values lower than 0.5 with yellow overlay included speed limit 20, speed limit 100, right of way, danger, and pay attention to traffic signs.
- Signs with p values lower than 0.5 with blue overlay included only left turns allowed, driving on the right, and following the direction.
- Signs with p values lower than 0.5 with yellow overlay included no right of way.
3.3. Gaussian Noise
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Pavlitska, S.; Lambing, N.; Zöllner, J.M. Adversarial Attacks on Traffic Sign Recognition: A Survey. In Proceedings of the 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering, Tenerife, Spain, 19–21 July 2023. [Google Scholar]
- Jia, W.; Lu, Z.; Zhang, H.; Liu, Z.; Wang, J.; Qu, G. Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems. In Proceedings of the Annual Network and Distributed System Security Symposium, San Diego, CA, USA, 24–28 April 2022. [Google Scholar]
- Shen, Y.; Cheng, Y.; Lin, Y.; Long, S.; Jiang, C.; Li, D.; Dai, S.; Jiang, Y.; Fang, J.; Jiang, Z.L.; et al. MLIA: Modulated LED Illumination-based Adversarial Attack on Traffic Sign Recognition System for Autonomous Vehicle. In Proceedings of the IEEE International Conference on Trust, Security and Privacy in Computing and Communications, Wuhan, China, 9–11 December 2022. [Google Scholar]
- Goodfellow, I.J.; Shlens, J.; Szegedy, C. Explaining and Harnessing Adversarial Examples. In Proceedings of the International Conference on Learning Representations, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Song, W.; Suandi, S.A. Sign-YOLO: A Novel Lightweight Detection Model for Chinese Traffic Sign. IEEE Access 2023, 11, 113941–113951. [Google Scholar] [CrossRef]
- Gholamy, A.; Kreinovich, V.; Kosheleva, O. Why 70/30 or 80/20 Relation Between Training and Testing Sets: A Pedagogical Explanation. Int. J. Intell. Technol. Appl. Stat. 2018, 11, 105–111. [Google Scholar]
- Xu, Y. On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. J. Anal. Test. 2018, 2, 249–262. [Google Scholar] [CrossRef] [PubMed]
- Khan, S.W.; Hafeez, Q.; Khalid, M.I.; Alroobaea, R.; Hussain, S.; Iqbal, J.; Almotiri, J.; Ullah, S.S. Anomaly Detection in Traffic Surveillance Videos Using Deep Learning. Sensors 2022, 22, 6563. [Google Scholar] [CrossRef] [PubMed]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 779–788. [Google Scholar]
- Pangakis, N.; Wolken, S.; Fasching, N. Automated Annotation with Generative AI Requires Validation. arXiv 2023, arXiv:2306.00176. [Google Scholar]
Evaluation | Criteria | |
---|---|---|
Precision (p) | Recall (r) | |
p, r > 0.8 | Most of the predicted categories are correct, and it is a good model. | Most of the detected objects are correct, and it is a good model. |
0.5 ≤ p, r ≤ 0.8 | The predicted category is generally correct, and it is an average model. | The detected objects are generally correct, and it is an average model. |
p, r < 0.5 | There are many errors in the predict results, and it is a poor model. | There are many errors in detecting objects, and it is a poor model. |
Outcome | Evaluation Criteria | ||
---|---|---|---|
Poor | Average | Good | |
Number of signs | 43 | 0 | 0 |
Outcome | Evaluation Criteria | ||
---|---|---|---|
Poor | Average | Good | |
Red | 28 | 14 | 1 |
Blue | 21 | 19 | 3 |
Yellow | 34 | 7 | 2 |
Green | 17 | 25 | 1 |
η | Evaluation Criteria | ||
---|---|---|---|
Poor | Average | Good | |
0.01 | 7 | 24 | 12 |
0.03 | 7 | 24 | 12 |
0.05 | 20 | 23 | 0 |
0.07 | 29 | 14 | 0 |
0.10 | 34 | 9 | 0 |
0.13 | 37 | 6 | 0 |
0.15 | 38 | 5 | 0 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lin, C.-H.; Yu, C.-T.; Chen, Y.-L.; Lin, Y.-Y.; Chiao, H.-T. Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles. Eng. Proc. 2025, 92, 15. https://doi.org/10.3390/engproc2025092015
Lin C-H, Yu C-T, Chen Y-L, Lin Y-Y, Chiao H-T. Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles. Engineering Proceedings. 2025; 92(1):15. https://doi.org/10.3390/engproc2025092015
Chicago/Turabian StyleLin, Chu-Hsing, Chao-Ting Yu, Yan-Ling Chen, Yo-Yu Lin, and Hsin-Ta Chiao. 2025. "Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles" Engineering Proceedings 92, no. 1: 15. https://doi.org/10.3390/engproc2025092015
APA StyleLin, C.-H., Yu, C.-T., Chen, Y.-L., Lin, Y.-Y., & Chiao, H.-T. (2025). Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles. Engineering Proceedings, 92(1), 15. https://doi.org/10.3390/engproc2025092015