EVALUATION OF THE ROBUSTNESS OF OBJECT DETECTION MODELS AGAIUST ADVERSARIAL ATTACKS

Authors

Keywords: FGSM, YOLOv5, PGD, Faster R-CNN, ResNet18, CNN

Abstract

In this study, object detection systems based on convolutional neural networks were investigated, particularly the effectiveness of adversarial attacks against the YOLOv5 model. As attack methods, the Fast Gradient Sign Method (FGSM) and its improved variants (Iterative FGSM and PGD) were applied. Adversarial perturbations generated using the ResNet18 model were used to compare the object detection results of the original image and the attacked image. The results demonstrated that even a small amount of noise can significantly mislead an object detection model. Adversarial attacks represent one of the major vulnerabilities of artificial intelligence models, especially deep learning–based image recognition systems. Attacks such as FGSM and PGD modify the model input with small perturbations, forcing the model to produce incorrect classifications.

References

1. Goodfellow I., Shlens J., Szegedy C. Explaining and harnessing adversarial examples. // arXiv preprint arXiv:1412.6572. 2014. https://arxiv.org/abs/1412.6572

2. Szegedy C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. Intriguing properties of neural networks. // arXiv preprint arXiv:1312.6199. 2013. https://arxiv.org/abs/1312.6199

3. Kurakin A., Goodfellow I., Bengio, S. Adversarial machine learning at scale. // arXiv preprint arXiv:1611.01236. 2016. https://arxiv.org/abs/1611.01236

4. Madry A., Makelov A., Schmidt L., Tsipras D., Vladu A. Towards deep learning models resistant to adversarial attacks. Proceedings of the 6th International Conference on Learning Representations (ICLR). 2018.

5. Papernot N., McDaniel P., Goodfellow I., Jha S., Celik Z.B., Swami A. Practical black-box attacks against deep learning systems using adversarial examples. // IEEE Symposium on Security and Privacy (SP), 2017. – P. 1-18.