Abstract
In recent times, deep neural networks are being used in a wide variety of applications such as autonomous vehicles, medical imaging and surveillance. While they are becoming increasingly powerful, it is possible to disrupt their task by crafting adversarial inputs. These inputs are essentially perturbations added to the original inputs so that the application using the network, such as an object recognizer, is unable to classify the object in the image. Crafting such inputs to disrupt such a recognition task is termed an adversarial attack. Here, we implement two disruption strategies, Fast Gradient Sign Method (FGSM) and generating perturbations using a generator network. While FGSM requires access to the gradient calculated by the classifier with respect to the input image, the generator trains simultaneously with the classifier network to learn how to craft perturbations. Once the generator network is trained with a particular classifier (say, VGG16), it can disrupt other classifier networks in a black-box fashion as well. Using the same dataset, in this case CIFAR-10, it is possible to adversarially train the classifier to make it more robust to perturbed images. This involves training the classifier on the CIFAR-10 images with both the original images and the ones perturbed by the generator. In experiments, the attack using the generator achieves higher disruption accuracies than FGSM on very deep networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Crafting Adversarial Attacks with Adversarial Transformations. https://github.com/kawine/atgan
Lee, H., Han, S., Lee, J.: Generative adversarial trainer: defense to adversarial perturbations with GAN. arXiv preprint arXiv:1705.03387 (2017)
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)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural İnformation Processing Systems, pp. 2672–2680 (2014)
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against machine learning. In: Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, pp. 506–519. ACM (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (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)
Baluja, S., Fischer, I.: Adversarial transformation networks: learning to generate adversarial examples. arXiv preprint arXiv:1703.09387 (2017)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Nair, V., Hinton, G.: The cifar-10 dataset (2014). http://www.cs.toronto.edu/kriz/cifar.html
Shen, S., Jin, G., Gao, K., Zhang, Y.: APE-GAN: adversarial perturbation elimination with GAN. arXiv:1707.05474 [cs.CV] (2017)
Computer vision. https://en.wikipedia.org/wiki/Computer_vision#Applications
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Das, U., Gupta, A., Bagga, O.S., Sabnis, M. (2020). Disruption of Object Recognition Systems. In: Pandian, A., Ntalianis, K., Palanisamy, R. (eds) Intelligent Computing, Information and Control Systems. ICICCS 2019. Advances in Intelligent Systems and Computing, vol 1039. Springer, Cham. https://doi.org/10.1007/978-3-030-30465-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-30465-2_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30464-5
Online ISBN: 978-3-030-30465-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)