Advertisement

Improved Adversarial Training via Learned Optimizer

Conference paper
  • 588 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12353)

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.

Keywords

Optimization Adversarial training Learning to learn 

Supplementary material

504445_1_En_6_MOESM1_ESM.pdf (195 kb)
Supplementary material 1 (pdf 195 KB)

References

  1. 1.
    Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: Advances in Neural Information Processing Systems, pp. 3981–3989 (2016)Google Scholar
  2. 2.
    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)Google Scholar
  3. 3.
    Brendel, W., Rauber, J., Bethge, M.: Decision-based adversarial attacks: reliable attacks against black-box machine learning models. arXiv preprint arXiv:1712.04248 (2017)
  4. 4.
    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)Google Scholar
  5. 5.
    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)
  6. 6.
    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)Google Scholar
  7. 7.
    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)Google Scholar
  8. 8.
    Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. arXiv preprint arXiv:1808.05377 (2018)
  9. 9.
    Engstrom, L., Ilyas, A., Athalye, A.: Evaluating and understanding the robustness of adversarial logit pairing. arXiv preprint arXiv:1807.10272 (2018)
  10. 10.
    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)Google Scholar
  11. 11.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
  12. 12.
    Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. arXiv preprint arXiv:1907.07174 (2019)
  13. 13.
    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)Google Scholar
  14. 14.
    Jiang, H., Chen, Z., Shi, Y., Dai, B., Zhao, T.: Learning to defense by learning to attack. arXiv preprint arXiv:1811.01213 (2018)
  15. 15.
    Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian Institute for Advanced Research), 8 (2010). http://www.cs.toronto.edu/~kriz/cifar.html
  16. 16.
    Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
  17. 17.
    Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)
  18. 18.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  19. 19.
    Lee, H., Han, S., Lee, J.: Generative adversarial trainer: defense to adversarial perturbations with GAN. arXiv preprint arXiv:1705.03387 (2017)
  20. 20.
    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)Google Scholar
  21. 21.
    Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
  22. 22.
    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)Google Scholar
  23. 23.
    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)Google Scholar
  24. 24.
    Nocedal, J., Wright, S.: Numerical Optimization. Springer Science & Business Media, New York (2006).  https://doi.org/10.1007/978-0-387-40065-5CrossRefzbMATHGoogle Scholar
  25. 25.
    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)Google Scholar
  26. 26.
    Ruan, Y., Xiong, Y., Reddi, S., Kumar, S., Hsieh, C.J.: Learning to learn by zeroth-order oracle. arXiv preprint arXiv:1910.09464 (2019)
  27. 27.
    Samangouei, P., Kabkab, M., Chellappa, R.: Defense-GAN: protecting classifiers against adversarial attacks using generative models. arXiv preprint arXiv:1805.06605 (2018)
  28. 28.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  29. 29.
    Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., Madry, A.: Robustness may be at odds with accuracy. arXiv preprint arXiv:1805.12152 (2018)
  30. 30.
    Wang, H., Yu, C.N.: A direct approach to robust deep learning using adversarial networks. arXiv preprint arXiv:1905.09591 (2019)
  31. 31.
    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)Google Scholar
  32. 32.
    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)Google Scholar
  33. 33.
    Wu, Y., Ren, M., Liao, R., Grosse, R.: Understanding short-horizon bias in stochastic meta-optimization. arXiv preprint arXiv:1803.02021 (2018)
  34. 34.
    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)Google Scholar
  35. 35.
    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)Google Scholar
  36. 36.
    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)Google Scholar
  37. 37.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
  38. 38.
    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)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of CaliforniaLos AngelesUSA

Personalised recommendations