Abstract
Adversarial attack has recently become a tremendous threat to deep learning models. To improve the robustness of machine learning models, adversarial training, formulated as a minimax optimization problem, has been recognized as one of the most effective defense mechanisms. However, the non-convex and non-concave property poses a great challenge to the minimax training. In this paper, we empirically demonstrate that the commonly used PGD attack may not be optimal for inner maximization, and improved inner optimizer can lead to a more robust model. Then we leverage a learning-to-learn (L2L) framework to train an optimizer with recurrent neural networks, providing update directions and steps adaptively for the inner problem. By co-training optimizer’s parameters and model’s weights, the proposed framework consistently improves over PGD-based adversarial training and TRADES.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981–3989 (2016)
Athalye, A., Carlini, N., Wagner, D.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: International Conference on Machine Learning, pp. 274–283 (2018)
Brendel, W., Rauber, J., Bethge, M.: Decision-based adversarial attacks: reliable attacks against black-box machine learning models. arXiv preprint arXiv:1712.04248 (2017)
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)
Cheng, M., Le, T., Chen, P.Y., Yi, J., Zhang, H., Hsieh, C.J.: Query-efficient hard-label black-box attack: an optimization-based approach. arXiv preprint arXiv:1807.04457 (2018)
Cheng, M., Singh, S., Chen, P.H., Chen, P.Y., Liu, S., Hsieh, C.J.: Sign-OPT: a query-efficient hard-label adversarial attack. In: ICLR (2020)
Cotter, N.E., Conwell, P.R.: Fixed-weight networks can learn. In: 1990 IJCNN International Joint Conference on Neural Networks, pp. 553–559. IEEE (1990)
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. arXiv preprint arXiv:1808.05377 (2018)
Engstrom, L., Ilyas, A., Athalye, A.: Evaluating and understanding the robustness of adversarial logit pairing. arXiv preprint arXiv:1807.10272 (2018)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1126–1135. JMLR.org (2017)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. arXiv preprint arXiv:1907.07174 (2019)
Jang, Y., Zhao, T., Hong, S., Lee, H.: Adversarial defense via learning to generate diverse attacks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2740–2749 (2019)
Jiang, H., Chen, Z., Shi, Y., Dai, B., Zhao, T.: Learning to defense by learning to attack. arXiv preprint arXiv:1811.01213 (2018)
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian Institute for Advanced Research), 8 (2010). http://www.cs.toronto.edu/~kriz/cifar.html
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, H., Han, S., Lee, J.: Generative adversarial trainer: defense to adversarial perturbations with GAN. arXiv preprint arXiv:1705.03387 (2017)
Lv, K., Jiang, S., Li, J.: Learning gradient descent: better generalization and longer horizons. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2247–2255. JMLR.org (2017)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Metz, L., Maheswaranathan, N., Nixon, J., Freeman, D., Sohl-Dickstein, J.: Understanding and correcting pathologies in the training of learned optimizers. In: International Conference on Machine Learning, pp. 4556–4565 (2019)
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)
Nocedal, J., Wright, S.: Numerical Optimization. Springer Science & Business Media, New York (2006). https://doi.org/10.1007/978-0-387-40065-5
Reddy Mopuri, K., Ojha, U., Garg, U., Venkatesh Babu, R.: NAG: network for adversary generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 742–751 (2018)
Ruan, Y., Xiong, Y., Reddi, S., Kumar, S., Hsieh, C.J.: Learning to learn by zeroth-order oracle. arXiv preprint arXiv:1910.09464 (2019)
Samangouei, P., Kabkab, M., Chellappa, R.: Defense-GAN: protecting classifiers against adversarial attacks using generative models. arXiv preprint arXiv:1805.06605 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., Madry, A.: Robustness may be at odds with accuracy. arXiv preprint arXiv:1805.12152 (2018)
Wang, H., Yu, C.N.: A direct approach to robust deep learning using adversarial networks. arXiv preprint arXiv:1905.09591 (2019)
Wang, J., Zhang, H.: Bilateral adversarial training: towards fast training of more robust models against adversarial attacks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6629–6638 (2019)
Wichrowska, O., et al.: Learned optimizers that scale and generalize. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3751–3760. JMLR.org (2017)
Wu, Y., Ren, M., Liao, R., Grosse, R.: Understanding short-horizon bias in stochastic meta-optimization. arXiv preprint arXiv:1803.02021 (2018)
Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., Song, D.: Generating adversarial examples with adversarial networks. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 3905–3911 (2018)
Xie, C., Wu, Y., van der Maaten, L., Yuille, A.L., He, K.: Feature denoising for improving adversarial robustness. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 501–509 (2019)
Younger, A.S., Hochreiter, S., Conwell, P.R.: Meta-learning with backpropagation. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN 2001 (Cat. No. 01CH37222), vol. 3. IEEE (2001)
Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
Zhang, H., Yu, Y., Jiao, J., Xing, E.P., Ghaoui, L.E., Jordan, M.I.: Theoretically principled trade-off between robustness and accuracy. arXiv preprint arXiv:1901.08573 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Xiong, Y., Hsieh, CJ. (2020). Improved Adversarial Training via Learned Optimizer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12353. Springer, Cham. https://doi.org/10.1007/978-3-030-58598-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-58598-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58597-6
Online ISBN: 978-3-030-58598-3
eBook Packages: Computer ScienceComputer Science (R0)