Skip to main content

2020 | OriginalPaper | Buchkapitel

Adversarial Defense via Attention-Based Randomized Smoothing

verfasst von : Xiao Xu, Shiyu Feng, Zheng Wang, Lizhe Xie, Yining Hu

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

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Recent works have shown the effectiveness of randomized smoothing in adversarial defense. This paper presents a new understanding of randomized smoothing. Features that are vulnerable to noise are not conducive to the prediction of model under adversarial perturbations. An enhanced defense called Attention-based Randomized Smoothing (ARS) is proposed. Based on smoothed classifier, ARS designs a mixed attention module, which helps model merge smoothed feature with original feature and pay more attention to robust feature. The advantages of ARS are manifested in four ways: 1) Superior performance on both clean and adversarial samples. 2) Without pre-processing in inference. 3) Explicable attention map. 4) Compatible with other defense methods. Experiment results demonstrate that ARS achieves the state-of-the-art defense against adversarial attacks on MNIST and CIFAR-10 datasets, outperforming Salman’s defense when the attacks are limited to a maximum norm.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

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!

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!

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!

Literatur
1.
Zurück zum Zitat Nguyen A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015) Nguyen A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)
2.
Zurück zum Zitat Cohen, J.M., Rosenfeld, E., Kolter, Z.: Certified adversarial robustness via randomized smoothing. arXiv preprint arXiv:1902.02918 (2019) Cohen, J.M., Rosenfeld, E., Kolter, Z.: Certified adversarial robustness via randomized smoothing. arXiv preprint arXiv:​1902.​02918 (2019)
3.
Zurück zum Zitat Salman, H., et al.: Provably robust deep learning via adversarially trained smoothed classifiers. In: Advances in Neural Information Processing Systems, pp. 11289–11300 (2019) Salman, H., et al.: Provably robust deep learning via adversarially trained smoothed classifiers. In: Advances in Neural Information Processing Systems, pp. 11289–11300 (2019)
4.
Zurück zum Zitat Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. arXiv preprint arXiv:1905.02175 (2019) Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. arXiv preprint arXiv:​1905.​02175 (2019)
5.
Zurück zum Zitat Wu, S., et al.: Attention, please! adversarial defense via attention rectification and preservation. arXiv preprint arXiv:1811.09831 (2018) Wu, S., et al.: Attention, please! adversarial defense via attention rectification and preservation. arXiv preprint arXiv:​1811.​09831 (2018)
6.
Zurück zum Zitat Goodman, D., Li, X., Huan, J., Wei, T.: Improving adversarial robustness via attention and adversarial logit pairing. arXiv preprint arXiv:1908.11435 (2019) Goodman, D., Li, X., Huan, J., Wei, T.: Improving adversarial robustness via attention and adversarial logit pairing. arXiv preprint arXiv:​1908.​11435 (2019)
7.
Zurück zum Zitat 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: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017) 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: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
8.
Zurück zum Zitat Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (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)
10.
Zurück zum Zitat Rony, J., Hafemann, L.G., Oliveira, L.S., Ayed, I.B., Sabourin, R., Granger, E.: Decoupling direction and norm for efficient gradient-based l2 adversarial attacks and defenses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4322–4330 (2019) Rony, J., Hafemann, L.G., Oliveira, L.S., Ayed, I.B., Sabourin, R., Granger, E.: Decoupling direction and norm for efficient gradient-based l2 adversarial attacks and defenses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4322–4330 (2019)
12.
Zurück zum Zitat Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. arXiv preprint arXiv:1711.01991 (2017) Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. arXiv preprint arXiv:​1711.​01991 (2017)
13.
Zurück zum Zitat Mustafa, A., Khan, S.H., Hayat, M., Shen, J., Shao, L.: Image super-resolution as a defense against adversarial attacks. arXiv preprint arXiv:1901.01677 (2019) Mustafa, A., Khan, S.H., Hayat, M., Shen, J., Shao, L.: Image super-resolution as a defense against adversarial attacks. arXiv preprint arXiv:​1901.​01677 (2019)
14.
Zurück zum Zitat Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018) Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
15.
Zurück zum Zitat 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) 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)
16.
Zurück zum Zitat 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) 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)
Metadaten
Titel
Adversarial Defense via Attention-Based Randomized Smoothing
verfasst von
Xiao Xu
Shiyu Feng
Zheng Wang
Lizhe Xie
Yining Hu
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-61609-0_36