Abstract
Owing to the recent remarkable advancements in computer vision and artificial intelligence, resilient self-driving cars are now becoming a reality. In this paper, we detail an autonomous car prototype that uses vision-based perception for control and navigation. The car uses a deep neural network to classify traffic symbols based on which motor control decisions are taken. The classification model is tested in various environmental settings and is observed to be robust. In real-world situations, misclassification in autonomous systems can lead to serious accidents. Although the classification model is reliable, there may arise different environmental scenarios where misclassification can occur. In order to simulate such a scenario, we explore the effects of different adversarial attacks on the network. It is observed that the attacks are able to trick the network into misclassifying symbols. Therefore, a network defense mechanism is crucial for handling such scenarios. We present a structure-based learning approach for a robust defense mechanism. The approach is self-supervised and it leverages the use of data augmentations of a sample to have different representations of the same. This ensures that the network is trained to learn the base structure for various environmental settings, thereby nullifying the effect of different adversarial attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6, 14410–14430 (2018)
Bai, T., Luo, J., Zhao, J., Wen, B., Wang, Q.: Recent advances in adversarial training for adversarial robustness. arXiv preprint arXiv:2102.01356 (2021)
Bakhti, Y., Fezza, S.A., Hamidouche, W., Déforges, O.: DDSA: a defense against adversarial attacks using deep denoising sparse autoencoder. IEEE Access 7, 160397–160407 (2019)
Brahmbhatt, S.: Practical OpenCV. Apress (2013)
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security And Privacy (SP), pp. 39–57. IEEE (2017)
Chakraborty, A., Alam, M., Dey, V., Chattopadhyay, A., Mukhopadhyay, D.: A survey on adversarial attacks and defences. CAAI Trans. Intell. Technol. 6(1), 25–45 (2021)
Croce, F., Hein, M.: Minimally distorted adversarial examples with a fast adaptive boundary attack. In: International Conference on Machine Learning, pp. 2196–2205. PMLR (2020)
Eykholt, K., et al.: Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1625–1634 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hemateja, A.V.N.M.: Traffic sign dataset - classification (2021). https://www.kaggle.com/datasets/ahemateja19bec1025/traffic-sign-dataset-classification?resource=download
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: Artificial Intelligence Safety and Security, pp. 99–112. Chapman and Hall/CRC (2018)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: DeepFool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The German traffic sign recognition benchmark: a multi-class classification competition. In: The 2011 International Joint Conference on Neural Networks, pp. 1453–1460. IEEE (2011)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Xu, H., et al.: Adversarial attacks and defenses in images, graphs and text: a review. Int. J. Autom. Comput. 17(2), 151–178 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sharma, M.K., Choudhuri, R., Dixit, M., Sarkar, M., Dittakavi, B. (2023). Structure-Based Learning for Robust Defense Against Adversarial Attacks in Autonomous Driving Agents. In: Gupta, D., Bhurchandi, K., Murala, S., Raman, B., Kumar, S. (eds) Computer Vision and Image Processing. CVIP 2022. Communications in Computer and Information Science, vol 1777. Springer, Cham. https://doi.org/10.1007/978-3-031-31417-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-31417-9_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31416-2
Online ISBN: 978-3-031-31417-9
eBook Packages: Computer ScienceComputer Science (R0)