Top

Published in:

2020 | OriginalPaper | Chapter

Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise

Authors : Alex Serban, Erik Poll, Joost Visser

Published in: Artificial Neural Networks and Machine Learning – ICANN 2020

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most compelling defense, adversarial training, requires a substantial increase in processing time and it has been shown to overfit on the training data. In this paper, we aim to overcome these limitations by training robust models in low data regimes and transfer adversarial knowledge between different models. We train a meta-optimizer which learns to robustly optimize a model using adversarial examples and is able to transfer the knowledge learned to new models, without the need to generate new adversarial examples. Experimental results show the meta-optimizer is consistent across different architectures and data sets, suggesting it is possible to automatically patch adversarial vulnerabilities.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

previous chapter Adversarial Defense via Attention-Based Randomized Smoothing

next chapter Unsupervised Anomaly Detection with a GAN Augmented Autoencoder

Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. In: NeurIPS, pp. 3981–3989 (2016)

Athalye, A., Carlini, N., Wagner, D.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: ICML (2018)

Bubeck, S., Price, E., Razenshteyn, I.: Adversarial examples from computational constraints. arXiv:1805.10204 (2018)

Carlini, N., et al.: On evaluating adversarial robustness. arXiv:1902.06705 (2019). http://arxiv.org/abs/1902.06705

Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (S&P), pp. 39–57. IEEE (2017)

Cullina, D., Bhagoji, A.N., Mittal, P.: PAC-learning in the presence of evasion adversaries. arXiv:1806.01471 (2018)

Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135 (2017)

Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv:1412.6572 (2014)

Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: ICLR (2019)

10.

Huang, X., et al.: Safety and trustworthiness of deep neural networks: a survey. arXiv:1812.08342 (2018)

11.

Jacobsen, J.H., Behrmann, J., Carlini, N., Florian Tramer, N.: Exploiting excessive invariance caused by norm-bounded adversarial robustness. In: ICLR (2019)

12.

Jacobsen, J.H., Behrmann, J., Zemel, R., Bethge, M.: Excessive invariance causes adversarial vulnerability. In: ICLR (2019)

13.

Katz, G., Barrett, C., Dill, D.L., Julian, K., Kochenderfer, M.J.: Reluplex: an efficient SMT solver for verifying deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 97–117. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63387-9_5CrossRef

14.

Li, K., Malik, J.: Learning to optimize. arXiv:1606.01885 (2016)

15.

Li, K., Malik, J.: Learning to optimize neural nets. arXiv:1703.00441 (2017)

16.

Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR (2018)

17.

Mirman, M., Gehr, T., Vechev, M.: Differentiable abstract interpretation for provably robust neural networks. In: ICML (2018)

18.

Miyato, T., Maeda, S.I., Koyama, M., Nakae, K., Ishii, S.: Distributional smoothing with virtual adversarial training. arXiv:1507.00677 (2015)

19.

Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)

20.

Rice, L., Wong, E., Kolter, J.Z.: Overfitting in adversarially robust deep learning. arXiv preprint arXiv:2002.11569 (2020)

21.

Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: ICML, pp. 1842–1850 (2016)

22.

Schmidhuber, J.: A neural network that embeds its own meta-levels. In: ICNN, pp. 407–412. IEEE (1993)

23.

Shafahi, A., et al.: Adversarial training for free! arXiv:1904.12843 (2019)

24.

Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., Madry, A.: There is no free lunch in adversarial robustness (but there are unexpected benefits). arXiv:1805.12152 (2018)

25.

Wichrowska, O., et al.: Learned optimizers that scale and generalize. In: ICML, pp. 3751–3760 (2017)

26.

Wong, E., Kolter, J.Z.: Provable defenses against adversarial examples via the convex outer adversarial polytope. In: ICML (2018)

27.

Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: Revisiting adversarial training. arXiv preprint arXiv:2001.03994 (2020)

28.

Younger, A.S., Hochreiter, S., Conwell, P.R.: Meta-learning with backpropagation. In: IJCNN, vol. 3. IEEE (2001)

29.

Zhang, D., Zhang, T., Lu, Y., Zhu, Z., Dong, B.: You only propagate once: accelerating adversarial training via maximal principle. arXiv:1905.00877 (2019)

30.

Zhang, H., Chen, H., Song, Z., Boning, D., Dhillon, I.S., Hsieh, C.J.: The limitations of adversarial training and the blind-spot attack. In: ICLR (2019)

Title: Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise
Authors: Alex Serban
Erik Poll
Joost Visser
Publisher: Springer International Publishing
Book: Artificial Neural Networks and Machine Learning – ICANN 2020
Print ISBN: 978-3-030-61608-3

Electronic ISBN: 978-3-030-61609-0

Copyright Year: 2020
DOI: https://doi.org/10.1007/978-3-030-61609-0_37

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner