Skip to main content

Robust Network Architecture Search via Feature Distortion Restraining

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

The vulnerability of Deep Neural Networks, i.e., susceptibility to adversarial attacks, severely limits the application of DNNs in security-sensitive domains. Most of existing methods improve model robustness from weight optimization, such as adversarial training. However, the architecture of DNNs is also a key factor to robustness, which is often neglected or underestimated. We propose Robust Network Architecture Search (RNAS) to obtain a robust network against adversarial attacks. We observe that an adversarial perturbation distorting the non-robust features in latent feature space can further aggravate misclassification. Based on this observation, we search the robust architecture through restricting feature distortion in the search process. Specifically, we define a network vulnerability metric based on feature distortion as a constraint in the search process. This process is modeled as a multi-objective bilevel optimization problem and a novel algorithm is proposed to solve this optimization. Extensive experiments conducted on CIFAR-10/100 and SVHN show that RNAS achieves the best robustness under various adversarial attacks compared with extensive baselines and SOTA methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Andriushchenko, M., Croce, F., Flammarion, N., Hein, M.: Square attack: a query-efficient black-box adversarial attack via random search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 484–501. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58592-1_29

    Chapter  Google Scholar 

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

    Google Scholar 

  3. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 801–818 (2018)

    Google Scholar 

  4. Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive differentiable architecture search: bridging the depth gap between search and evaluation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1294–1303 (2019)

    Google Scholar 

  5. Croce, F., Hein, M.: Minimally distorted adversarial examples with a fast adaptive boundary attack. In: International Conference on Machine Learning, pp. 2196–2205 (2020)

    Google Scholar 

  6. Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: International Conference on Machine Learning, pp. 2206–2216 (2020)

    Google Scholar 

  7. Devaguptapu, C., Agarwal, D., Mittal, G., Balasubramanian, V.N.: An empirical study on the robustness of NAS based architectures. arXiv preprint arXiv:2007.08428 (2020)

  8. Dong, M., Li, Y., Wang, Y., Xu, C.: Adversarially robust neural architectures. arXiv preprint arXiv:2009.00902 (2020)

  9. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1097–1105 (2014)

    Google Scholar 

  10. Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015)

    Google Scholar 

  11. Guo, M., Yang, Y., Xu, R., Liu, Z., Lin, D.: When NAS meets robustness: in search of robust architectures against adversarial attacks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 628–637 (2020)

    Google Scholar 

  12. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  13. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Advances in 28th Neural Information Processing Systems (2015)

    Google Scholar 

  14. Hosseini, R., Yang, X., Xie, P.: DSRNA: differentiable search of robust neural architectures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6196–6205 (2021)

    Google Scholar 

  15. Huang, G., Liu, Z., Maaten, L., Q, K.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)

    Google Scholar 

  16. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  17. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50\(\times \) fewer parameters and \({<}\)0.5 MB model size. In: International Conference on Learning Representations (2017)

    Google Scholar 

  18. Ilyas, A., Santurkar, S., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  19. Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Technical Report (2009)

    Google Scholar 

  20. Krizhevsky, A., Ilya, S., Geoffrey E.H.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  21. Kullback, S., Leibler, R.A.: On information and sufficiency. In: The Annals of Mathematical Statistics, pp. 79–86 (1951)

    Google Scholar 

  22. Lecuyer, M., Atlidakis, V., Geambasu, R., Hsu, D., Jana, S.: Certified robustness to adversarial examples with differential privacy. In: 2019 IEEE Symposium on Security and Privacy, pp. 656–672 (2019)

    Google Scholar 

  23. Liu, C., et al.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision, pp. 19–34 (2018)

    Google Scholar 

  24. Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019)

    Google Scholar 

  25. Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision, pp. 116–131 (2018)

    Google Scholar 

  26. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks (2017)

    Google Scholar 

  27. Mok, J., Na, B., Choe, H., Yoon, S.: AdvRush: searching for adversarially robust neural architectures. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12322–12332 (2021)

    Google Scholar 

  28. 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 (2017)

    Google Scholar 

  29. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Y, N.A.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)

    Google Scholar 

  30. Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against deep learning systems using adversarial examples. In: Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, pp. 506–519 (2017)

    Google Scholar 

  31. Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE Symposium on Security and Privacy, pp. 582–597 (2016)

    Google Scholar 

  32. Real, E., Aggarwal, A., Huang, Y., Le, Q.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4780–4789 (2019)

    Google Scholar 

  33. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  34. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large scale image recognition. In: International Conference on Learning Representations (2015)

    Google Scholar 

  35. Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)

  36. Tu, C.C., et al.: Autozoom: autoencoder-based zeroth order optimization method for attacking black-box neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 742–749 (2019)

    Google Scholar 

  37. Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. In: International Conference on Learning Representations (2020)

    Google Scholar 

  38. Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: International Conference on Learning Representations (2019)

    Google Scholar 

  39. Xu, Y., Xie, L., Zhang, X., Chen, X.: PC-DARTS: partial channel connections for memory-efficient architecture search. In: International Conference on Learning Representations (2019)

    Google Scholar 

  40. Zhang, H., Yu, Y., Jiao, J., Xing, E., Ghaoui, L.E., Jordan, M.I.: Theoretically principled trade-off between robustness and accuracy. In: International Conference on Machine Learning, pp. 7472–7482 (2019)

    Google Scholar 

  41. Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320–4328 (2018)

    Google Scholar 

  42. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: International Conference on Learning Representations (2017)

    Google Scholar 

  43. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)

    Google Scholar 

  44. Zugner, D., Akbarnejad, A., Gunnemann, S.: Adversarial attacks on neural networks for graph data. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2847–2856 (2018)

    Google Scholar 

Download references

Acknowledgment

This work is sponsored by the Zhejiang Provincial Natural Science Foundation of China (LZ22F020007, LGF20F020007), Major Research Plan of the National Natural Science Foundation of China (92167203), National Key R &D Program of China (2018YFB2100400), Natural Science Foundation of China (61902082, 61972357), and project funded by China Postdoctoral Science Foundation under No. 2022M713253.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Bin Wang .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Qian, Y. et al. (2022). Robust Network Architecture Search via Feature Distortion Restraining. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13665. Springer, Cham. https://doi.org/10.1007/978-3-031-20065-6_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20065-6_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20064-9

  • Online ISBN: 978-3-031-20065-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics