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.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
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
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy, pp. 39–57 (2017)
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)
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)
Croce, F., Hein, M.: Minimally distorted adversarial examples with a fast adaptive boundary attack. In: International Conference on Machine Learning, pp. 2196–2205 (2020)
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)
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)
Dong, M., Li, Y., Wang, Y., Xu, C.: Adversarially robust neural architectures. arXiv preprint arXiv:2009.00902 (2020)
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)
Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015)
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)
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)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Advances in 28th Neural Information Processing Systems (2015)
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)
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)
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)
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)
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)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Technical Report (2009)
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)
Kullback, S., Leibler, R.A.: On information and sufficiency. In: The Annals of Mathematical Statistics, pp. 79–86 (1951)
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)
Liu, C., et al.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision, pp. 19–34 (2018)
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019)
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)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks (2017)
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)
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)
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)
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)
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)
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)
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)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large scale image recognition. In: International Conference on Learning Representations (2015)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
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)
Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. In: International Conference on Learning Representations (2020)
Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: International Conference on Learning Representations (2019)
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)
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)
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)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: International Conference on Learning Representations (2017)
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)
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)
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
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)