Abstract
Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and – thanks to mature frameworks – relatively easy to implement and deploy. However, their reasoning is hidden inside a black box, in spite of a number of proposed approaches that try to provide human-understandable explanations for the predictions of neural networks. It is still a matter of debate which of these explainers are best suited for which situations, and how to quantitatively evaluate and compare them [1]. In this contribution, we focus on the capabilities of explainers for convolutional deep neural networks in an extreme situation: a setting in which humans and networks fundamentally disagree. Deep neural networks are susceptible to adversarial attacks that deliberately modify input samples to mislead a neural network’s classification, without affecting how a human observer interprets the input. Our goal with this contribution is to evaluate explainers by investigating whether they can identify adversarially attacked regions of an image. In particular, we quantitatively and qualitatively investigate the capability of three popular explainers of classifications – classic salience, guided backpropagation, and LIME – with respect to their ability to identify regions of attack as the explanatory regions for the (incorrect) prediction in representative examples from image classification. We find that LIME outperforms the other explainers.
This work was supported by Honda Research Institute Europe GmbH, Offenbach am Main, Germany.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mohseni, S., Zarei, N., Ragan, E.D.: A survey of evaluation methods and measures for interpretable machine learning (2018). arXiv:1811.11839
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Fischer, L., Hammer, B., Wersing, H.: Optimal local rejection for classifiers. Neurocomputing 214, 445–457 (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016). arXiv:1602.04938
Samek, W., Wiegand, T., Müller, K.-R.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models (2017). arXiv:1708.08296
Schulz, A., Gisbrecht, A., Hammer, B.: Using discriminative dimensionality reduction to visualize classifiers. Neural Process. Lett. 42, 27–54 (2014)
Göpfert, J.P., Wersing, H., Hammer, B.: Adversarial attacks hidden in plain sight (2019). arXiv:1902.09286
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: IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017)
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.A.: Striving for simplicity: the all convolutional net (2014). arXiv:1412.6806
Rauber, J., Brendel, W., Bethge, M.: Foolbox: a python toolbox to benchmark the robustness of machine learning models (2017). arXiv:1707.04131
Papernot, N., et al.: Technical report on the CleverHans v2.1.0 Adversarial Examples Library (2016). arXiv:1610.00768
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples (2014). arXiv:1412.6572
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial machine learning at scale (2016). arXiv:1611.01236
Bengio, Y., Courville, A.C., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798–1828 (2013)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59, 167–181 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Göpfert, J.P., Wersing, H., Hammer, B. (2019). Recovering Localized Adversarial Attacks. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation. ICANN 2019. Lecture Notes in Computer Science(), vol 11727. Springer, Cham. https://doi.org/10.1007/978-3-030-30487-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-30487-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30486-7
Online ISBN: 978-3-030-30487-4
eBook Packages: Computer ScienceComputer Science (R0)