Abstract
Concerns with the interpretability of ML models are growing as the technology is used in increasingly sensitive domains (e.g., health and public administration). Synthetic data can be used to understand models better, for instance, if the examples are generated close to the frontier between classes. However, data augmentation techniques, such as Generative Adversarial Networks (GAN), have been mostly used to generate training data that leads to better models. We propose a variation of GANs that, given a model, generates realistic data that is classified with low confidence by a given classifier. The generated examples can be used in order to gain insights on the frontier between classes. We empirically evaluate our approach on two well-known image classification benchmark datasets, MNIST and Fashion MNIST. Results show that the approach is able to generate images that are closer to the frontier when compared to the original ones, but still realistic. Manual inspection confirms that some of those images are confusing even for humans.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks, vol. 70, pp. 214–223. PMLR (2017). https://proceedings.mlr.press/v70/arjovsky17a.html
Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020). https://doi.org/10.1016/j.inffus.2019.12.012
Brown, T.B., Carlini, N., Zhang, C., Olsson, C., Christiano, P., Goodfellow, I.: Unrestricted adversarial examples (2018). https://doi.org/10.48550/ARXIV.1809.08352
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: Proceedings of the IEEE Symposium on Security and Privacy, pp. 39–57 (2016). https://doi.org/10.48550/arxiv.1608.04644
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database, pp. 248–255 (2010). https://doi.org/10.1109/CVPR.2009.5206848
Dunn, I., Pouget, H., Melham, T., Kroening, D.: Adaptive generation of unrestricted adversarial inputs (2019). https://doi.org/10.48550/arxiv.1905.02463
Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf
Goodfellow, I.J.: NIPS 2016 tutorial: generative adversarial networks. CoRR abs/1701.00160 (2017). https://arxiv.org/abs/1701.00160
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings (2014). https://doi.org/10.48550/arxiv.1412.6572. https://arxiv.org/abs/1412.6572v3
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/file/8a1d694707eb0fefe65871369074926d-Paper.pdf
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR abs/1411.1784 (2014). https://arxiv.org/abs/1411.1784
Mitchell, M., et al.: Model cards for model reporting. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019, pp. 220–229. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3287560.3287596
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs, vol. 70, pp. 2642–2651. PMLR (2017). https://proceedings.mlr.press/v70/odena17a.html
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings (2015). https://doi.org/10.48550/arxiv.1511.06434
Salimans, T., et al.: Improved techniques for training GANs, vol. 29. Curran Associates, Inc. (2016). https://proceedings.neurips.cc/paper/2016/file/8a3363abe792db2d8761d6403605aeb7-Paper.pdf
Song, Y., Shu, R., Kushman, N., Ermon, S.: Constructing unrestricted adversarial examples with generative models, vol. 31. Curran Associates, Inc. (2018). https://proceedings.neurips.cc/paper/2018/file/8cea559c47e4fbdb73b23e0223d04e79-Paper.pdf
Szegedy, C., et al.: Intriguing properties of neural networks. In: 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings (2013). https://doi.org/10.48550/arxiv.1312.6199. https://arxiv.org/abs/1312.6199v4
Tao, X., Hangcheng, L., Shangwei, G., Yan, G., Xiaofeng, L.: EGM: an efficient generative model for unrestricted adversarial examples. ACM Trans. Sens. Netw. (TOSN) (2021). https://doi.org/10.1145/3511893
Wang, X., He, K., Hopcroft, J.E.: AT-GAN: a generative attack model for adversarial transferring on generative adversarial nets. CoRR abs/1904.07793 (2019). https://arxiv.org/abs/1904.07793
Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., Song, D.: Generating adversarial examples with adversarial networks. In: IJCAI International Joint Conference on Artificial Intelligence 2018-July, pp. 3905–3911 (2018). https://doi.org/10.48550/arxiv.1801.02610
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR abs/1708.07747 (2017). https://arxiv.org/abs/1708.07747
Zhao, Z., Dua, D., Singh, S.: Generating natural adversarial examples. In: 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings (2017). https://doi.org/10.48550/arxiv.1710.11342
Acknowledgements
This work was partially funded by projects AISym4Med (101095387) supported by Horizon Europe Cluster 1: Health, ConnectedHealth (n.\(^{\underline{\text {o}}}\) 46858), supported by Competitiveness and Internationalisation Operational Programme (POCI) and Lisbon Regional Operational Programme (LISBOA 2020), under the PORTUGAL 2020 Partnership Agreement, through the European Regional Development Fund (ERDF) and NextGenAI - Center for Responsible AI (2022-C05i0102-02), supported by IAPMEI, and also by FCT plurianual funding for 2020–2023 of LIACC (UIDB/00027/2020_UIDP/00027/2020).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cunha, L., Soares, C., Restivo, A., Teixeira, L.F. (2023). GASTeN: Generative Adversarial Stress Test Networks. In: Crémilleux, B., Hess, S., Nijssen, S. (eds) Advances in Intelligent Data Analysis XXI. IDA 2023. Lecture Notes in Computer Science, vol 13876. Springer, Cham. https://doi.org/10.1007/978-3-031-30047-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-30047-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30046-2
Online ISBN: 978-3-031-30047-9
eBook Packages: Computer ScienceComputer Science (R0)