Abstract
Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches in training robust models against such attacks. However, it is much slower than vanilla training of neural networks since it needs to construct adversarial examples for the entire training data at every iteration, hampering its effectiveness. Recently, Fast Adversarial Training (FAT) was proposed that can obtain robust models efficiently. However, the reasons behind its success are not fully understood, and more importantly, it can only train robust models for \(\ell _\infty \)-bounded attacks as it uses FGSM during training. In this paper, by leveraging the theory of coreset selection, we show how selecting a small subset of training data provides a general, more principled approach toward reducing the time complexity of robust training. Unlike existing methods, our approach can be adapted to a wide variety of training objectives, including TRADES, \(\ell _p\)-PGD, and Perceptual Adversarial Training (PAT). Our experimental results indicate that our approach speeds up adversarial training by 2–3 times while experiencing a slight reduction in the clean and robust accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that adversarial training in the literature generally refers to a particular approach proposed by Madry et al. [25]. For the purposes of this paper, we refer to any method that builds adversarial attacks around the training data and incorporates them into the training of the neural network as adversarial training. Using this taxonomy, methods such as TRADES [44], \(\ell _p\)-PGD [25] or Perceptual Adversarial Training (PAT) [22] are all considered different versions of adversarial training.
- 2.
Our implementation can be found in this repository.
References
Adadi, A.: A survey on data-efficient algorithms in big data era. J. Big Data 8(1), 1–54 (2021). https://doi.org/10.1186/s40537-021-00419-9
Andriushchenko, M., Flammarion, N.: Understanding and improving fast adversarial training. In: Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS) (2020)
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., Roli, F.: Evasion attacks against machine learning at test time. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8190, pp. 387–402. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40994-3_25
Campbell, T., Broderick, T.: Bayesian coreset construction via greedy iterative geodesic ascent. In: Proceedings of the 35th International Conference on Machine Learning (ICML), pp. 697–705 (2018)
Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp. 2206–2216 (2020)
Danskin, J.M.: The Theory of Max-min and its Application to Weapons Allocation Problems, vol. 5. Springer Science & Business Media (1967). https://doi.org/10.1007/978-3-642-46092-0
Elenberg, E.R., Khanna, R., Dimakis, A.G., Negahban, S.N.: Restricted strong convexity implies weak submodularity. CoRR abs/1612.00804 (2016)
Eykholt, K., et al.: Robust physical-world attacks on deep learning visual classification. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1625–1634 (2018)
Feldman, D.: Introduction to core-sets: an updated survey. CoRR abs/2011.09384 (2020)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2015)
Har-Peled, S., Mazumdar, S.: On coresets for k-means and k-median clustering. In: Proceedings of the 36th Annual ACM Symposium on Theory of Computing (STOC), pp. 291–300 (2004)
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 (CVPR), pp. 770–778 (2016)
Kang, D., Sun, Y., Hendrycks, D., Brown, T., Steinhardt, J.: Testing robustness against unforeseen adversaries. CoRR abs/1908.08016 (2019)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8107–8116 (2020)
Katharopoulos, A., Fleuret, F.: Not all samples are created equal: Deep learning with importance sampling. In: Proceedings of the 35th International Conference on Machine Learning (ICML), pp. 2530–2539 (2018)
Killamsetty, K., Sivasubramanian, D., Ramakrishnan, G., De, A., Iyer, R.K.: GRAD-MATCH: gradient matching based data subset selection for efficient deep model training. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp. 5464–5474 (2021)
Killamsetty, K., Sivasubramanian, D., Ramakrishnan, G., Iyer, R.K.: GLISTER: generalization based data subset selection for efficient and robust learning. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 8110–8118 (2021)
Kolter, Z., Madry, A.: Adversarial robustness: theory and practice. In: Tutorial in the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems (NeurIPS) (2018). https://adversarial-ml-tutorial.org/
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master’s thesis, Department of Computer Science, University of Toronto (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the Advances in Neural Information Processing Systems 25: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 1106–1114 (2012)
Laidlaw, C., Feizi, S.: Functional adversarial attacks. In: Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 10408–10418 (2019)
Laidlaw, C., Singla, S., Feizi, S.: Perceptual adversarial robustness: defense against unseen threat models. In: Proceedings of the 9th International Conference on Learning Representations (ICLR) (2021)
Liu, Y., Ma, X., Bailey, J., Lu, F.: Reflection backdoor: a natural backdoor attack on deep neural networks. In: Proceedings of the 16th European Conference on Computer Vision (ECCV), pp. 182–199 (2020). https://doi.org/10.1007/978-3-030-58607-2_11
Ma, X., et al.: Understanding adversarial attacks on deep learning based medical image analysis systems. Pattern Recogn. 110, 107332 (2021)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
Minoux, M.: Accelerated greedy algorithms for maximizing submodular set functions. In: Optimization Techniques, pp. 234–243. Springer (1978). https://doi.org/10.1007/BFb0006528
Mirzasoleiman, B., Bilmes, J.A., Leskovec, J.: Coresets for data-efficient training of machine learning models. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp. 6950–6960 (2020)
Mirzasoleiman, B., Cao, K., Leskovec, J.: Coresets for robust training of deep neural networks against noisy labels. In: Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS) (2020)
Nemhauser, G.L., Wolsey, L.A., Fisher, M.L.: An analysis of approximations for maximizing submodular set functions - I. Math. Program. 14(1), 265–294 (1978). https://doi.org/10.1007/BF01588971
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NeurIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)
Pati, Y.C., Rezaiifar, R., Krishnaprasad, P.S.: Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. In: Proceedings of 27th Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 40–44 (1993)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. Commun. ACM, 63(12), 54–63 (2020)
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. In: Korhonen, A., Traum, D.R., Màrquez, L. (eds.) Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL), pp. 3645–3650 (2019)
Szegedy, C., et al.: Intriguing properties of neural networks. In: Proceedings of the 2nd International Conference on Learning Representations (ICLR) (2014)
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I.J., Boneh, D., McDaniel, P.D.: Ensemble adversarial training: Attacks and defenses. In: Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., Madry, A.: Robustness may be at odds with accuracy. In: Proceedings of the 7th International Conference on Learning Representations (ICLR) (2019)
Vahdat, A., Kautz, J.: NVAE: a deep hierarchical variational autoencoder. In: Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS) (2020)
Wei, K., Iyer, R., Bilmes, J.: Submodularity in data subset selection and active learning. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), pp. 1954–1963 (2015)
Wolsey, L.A.: An analysis of the greedy algorithm for the submodular set covering problem. Combinatorica 2(4), 385–393 (1982). https://doi.org/10.1007/BF02579435
Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. In: Proceedings of the 8th International Conference on Learning Representations (ICLR) (2020)
Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https://github.com/facebookresearch/detectron2
Xiao, C., Zhu, J., Li, B., He, W., Liu, M., Song, D.: Spatially transformed adversarial examples. In: Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
Zhang, H., Yu, Y., Jiao, J., Xing, E.P., Ghaoui, L.E., Jordan, M.I.: Theoretically principled trade-off between robustness and accuracy. In: Proceedings of the 36th International Conference on Machine Learning (ICML), pp. 7472–7482 (2019)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586–595 (2018)
Acknowledgements
This research was undertaken using the LIEF HPC-GPGPU Facility hosted at the University of Melbourne. This Facility was established with the assistance of LIEF Grant LE170100200.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dolatabadi, H.M., Erfani, S., Leckie, C. (2022). \(\ell _\infty \)-Robustness and Beyond: Unleashing Efficient Adversarial Training. 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 13671. Springer, Cham. https://doi.org/10.1007/978-3-031-20083-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-20083-0_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20082-3
Online ISBN: 978-3-031-20083-0
eBook Packages: Computer ScienceComputer Science (R0)