Adversarial Attacks and Defences: Ensuring Robustness in Machine Learning Systems

Authors

  • Gireesh Bhaulal Patil, Uday Krishna Padyana, Hitesh Premshankar Rai, Pavan Ogeti, Narendra Sharad Fadnavis, Rajesh Munirathnam

Keywords:

Deep learning and security, machine learning and adversarial attacks, deep learning vulnerability, methods for making AI models robust, neural network security

Abstract

The current paper aims at presenting and discussing adversarial attacks and defence mechanisms in learning models, especially Deep Learning. First, the types of adversarial attacks, the working principle, and the effects on diversified architectures are discussed in this paper. We explicate the current best practices in defence mechanisms and measuring robustness, including various application areas. Real life examples from classification of images, text analysis, and uses of self-driving cars elaborate the real-life issues as well as approaches. , Last but not the least, we discuss the trends, legal and ethical issues and research avenues in adversarial machine learning.

Downloads

Download data is not yet available.

References

Carlini, N., & Wagner, D. (2017). Towards evaluating the robustness of neural networks. In 2017 IEEE Symposium on Security and Privacy (SP) (pp. 39-57). IEEE. https://doi.org/10.1109/SP.2017.49

Goodfellow, I. J., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples. In International Conference on Learning Representations. https://arxiv.org/abs/1412.6572

Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations. https://arxiv.org/abs/1706.06083

Papernot, N., McDaniel, P., Wu, X., Jha, S., & Swami, A. (2016). Distillation as a defense to adversarial perturbations against deep neural networks. In 2016 IEEE Symposium on Security and Privacy (SP) (pp. 582-597). IEEE. https://doi.org/10.1109/SP.2016.41

Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks. In International Conference on Learning Representations. https://arxiv.org/abs/1312.6199

Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2018). Ensemble adversarial training: Attacks and defenses. In International Conference on Learning Representations. https://arxiv.org/abs/1705.07204

Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018). Robust physical-world attacks on deep learning visual classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1625-1634). https://doi.org/10.1109/CVPR.2018.00175

Athalye, A., Carlini, N., & Wagner, D. (2018). Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In International Conference on Machine Learning (pp. 274-283). PMLR. https://arxiv.org/abs/1802.00420

Guo, C., Rana, M., Cisse, M., & Van Der Maaten, L. (2018). Countering adversarial images using input transformations. In International Conference on Learning Representations. https://arxiv.org/abs/1711.00117

Shafahi, A., Najibi, M., Ghiasi, M. A., Xu, Z., Dickerson, J., Studer, C., Davis, L. S., Taylor, G., & Goldstein, T. (2019). Adversarial training for free! In Advances in Neural Information Processing Systems (pp. 3358-3369). https://arxiv.org/abs/1904.12843

Downloads

Published

06.08.2024

How to Cite

Gireesh Bhaulal Patil. (2024). Adversarial Attacks and Defences: Ensuring Robustness in Machine Learning Systems. International Journal of Intelligent Systems and Applications in Engineering, 12(23s), 217 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6726

Issue

Section

Research Article

Most read articles by the same author(s)