Abstract
Since the concept of adversarial attack was proposed, the vulnerability of Deep Neural Networks (DNNs) has attracted the interest of artificial intelligence researchers. Many state-of-the-art DNNs suffer the risk of adversarial perturbations, which can be divided into image-dependent and universal. In this paper, we review some traditional algorithms developed by others and introduce a novel method to create universal adversarial perturbations by attention. Our approach is the first to generate universal perturbations by attacking the attention heat maps with the interpretation method, Layer-wise Relevance Propagation. Our experiment results, when compared with traditional ones, showing an improvement both on fooling ratios and transferability with the ImageNet dataset. The goal of our research is to create less vulnerable DNNs to adversarial attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software available from tensorflow.org
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7) (2015)
Behjati, M., Moosavi-Dezfooli, S.-M., Baghshah, M.S., Frossard, P.: Universal adversarial attacks on text classifiers. In: ICASSP 2019—2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7345–7349. IEEE (2019)
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)
Chollet, F., et al.: Keras. https://keras.io (2015)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Hayes, J., Danezis, G.: Learning universal adversarial perturbations with generative models. In: 2018 IEEE Security and Privacy Workshops (SPW), pp. 43–49. IEEE (2018)
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)
Hendrik Metzen, J., Chaithanya Kumar, M., Brox, T., Fischer, V.: Universal adversarial perturbations against semantic image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2755–2764 (2017)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Kasabov, N.K.: Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence. Springer, Berlin, Heidelberg (2019)
Khrulkov, V., Oseledets, I.: Art of singular vectors and universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8562–8570 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Li, J., Ji, R., Liu, H., Hong, X., Gao, Y., Tian, Q.: Universal perturbation attack against image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4899–4908 (2019)
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Liu, H., Ji, R., Li, J., Zhang, B., Gao, Y., Wu, Y., Huang, F.: Universal adversarial perturbation via prior driven uncertainty approximation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2941–2949 (2019)
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Müller, K.-R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211–222 (2017)
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765–1773 (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)
Mopuri, K.R., Ganeshan, A., Venkatesh Babu, R.: Generalizable data-free objective for crafting universal adversarial perturbations. IEEE Trans. Pattern Anal. Mach. Intell. 41(10), 2452–2465 (2018)
Mopuri, K.R., Garg, U., Venkatesh Babu, R.: Fast feature fool: a data independent approach to universal adversarial perturbations. arXiv preprint arXiv:1707.05572 (2017)
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Berkay Celik, Z., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)
Poursaeed, O., Katsman, I., Gao, B., Belongie, S.: Generative adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4422–4431 (2018)
Russakovsky, O., Deng, J., Hao, S., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
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)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818–833. Springer (2014)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. arXiv preprint arXiv:1412.6856 (2014)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Zhou, J., Troyanskaya, O.G.: Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12(10), 931–934 (2015)
Acknowledgements
This research is partly supported by NSFC, China (Nos.: 61876107, U1803261, 61977046) and Committee of Science and Technology, Shanghai, China (No. 19510711200).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Wang, Z., Huang, X., Yang, J., Kasabov, N. (2022). Universal Adversarial Perturbation Generated by Using Attention Information. In: Sgurev, V., Jotsov, V., Kacprzyk, J. (eds) Advances in Intelligent Systems Research and Innovation. Studies in Systems, Decision and Control, vol 379. Springer, Cham. https://doi.org/10.1007/978-3-030-78124-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-78124-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78123-1
Online ISBN: 978-3-030-78124-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)