Advertisement

Boosting Decision-Based Black-Box Adversarial Attacks with Random Sign Flip

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12360)

Abstract

Decision-based black-box adversarial attacks (decision-based attack) pose a severe threat to current deep neural networks, as they only need the predicted label of the target model to craft adversarial examples. However, existing decision-based attacks perform poorly on the \( l_\infty \) setting and the required enormous queries cast a shadow over the practicality. In this paper, we show that just randomly flipping the signs of a small number of entries in adversarial perturbations can significantly boost the attack performance. We name this simple and highly efficient decision-based \( l_\infty \) attack as Sign Flip Attack. Extensive experiments on CIFAR-10 and ImageNet show that the proposed method outperforms existing decision-based attacks by large margins and can serve as a strong baseline to evaluate the robustness of defensive models. We further demonstrate the applicability of the proposed method on real-world systems.

Keywords

Adversarial examples Decision-based attacks 

Notes

Acknowledgement

This work was supported in part by the Major Project for New Generation of AI under Grant No. 2018AAA0100400, the National Natural Science Foundation of China (No. 61836014, No. 61761146004, No. 61773375).

Supplementary material

504470_1_En_17_MOESM1_ESM.pdf (625 kb)
Supplementary material 1 (pdf 625 KB)

References

  1. 1.
    Al-Dujaili, A., O’Reilly, U.M.: Sign bits are all you need for black-box attacks. In: Proceedings of International Conference on Learning Representations (2020)Google Scholar
  2. 2.
    Alzantot, M., Sharma, Y., Chakraborty, S., Srivastava, M.: Genattack: practical black-box attacks with gradient-free optimization. arXiv preprint arXiv:1805.11090 (2018)
  3. 3.
    Athalye, A., Carlini, N., Wagner, D.A.: Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: Proceedings of International Conference on Machine Learning (2018)Google Scholar
  4. 4.
    Athalye, A., Engstrom, L., Ilyas, A., Kwok, K.: Synthesizing robust adversarial examples. arXiv preprint arXiv:1707.07397 (2017)
  5. 5.
    Bhagoji, A.N., He, W., Li, B., Song, D.: Practical black-box attacks on deep neural networks using efficient query mechanisms. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 158–174. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01258-8_10CrossRefGoogle Scholar
  6. 6.
    Biggio, B., et al.: 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_25CrossRefGoogle Scholar
  7. 7.
    Brendel, W., Rauber, J., Bethge, M.: Decision-based adversarial attacks: reliable attacks against black-box machine learning models. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  8. 8.
    Buckman, J., Roy, A., Raffel, C., Goodfellow, I.: Thermometer encoding: one hot way to resist adversarial examples. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  9. 9.
    Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: Proceedings of the IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)Google Scholar
  10. 10.
    Chen, J., Jordan, M.I., Wainwright, M.: Hopskipjumpattack: a query-efficient decision-based attack. arXiv preprint arXiv:1904.02144 (2019)
  11. 11.
    Chen, P.Y., Zhang, H., Sharma, Y., Yi, J., Hsieh, C.J.: Zoo: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 15–26. ACM (2017)Google Scholar
  12. 12.
    Cheng, M., Le, T., Chen, P.Y., Yi, J., Zhang, H., Hsieh, C.J.: Query-efficient hard-label black-box attack: an optimization-based approach. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  13. 13.
    Cheng, M., Singh, S., Chen, P.Y., Liu, S., Hsieh, C.J.: Sign-opt: a query-efficient hard-label adversarial attack. In: Proceedings of International Conference on Learning Representations (2020)Google Scholar
  14. 14.
    Cheng, S., Dong, Y., Pang, T., Su, H., Zhu, J.: Improving black-box adversarial attacks with a transfer-based prior. In: Advances in Neural Information Processing Systems, pp. 10934–10944 (2019)Google Scholar
  15. 15.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)Google Scholar
  16. 16.
    Dong, Y., et al.: Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185–9193 (2018)Google Scholar
  17. 17.
    Dong, Y., et al.: Efficient decision-based black-box adversarial attacks on face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7714–7722 (2019)Google Scholar
  18. 18.
    Eykholt, K., et al.: Robust physical-world attacks on deep learning models. arXiv preprint arXiv:1707.08945 (2017)
  19. 19.
    Fan, Y., et al.: Sparse adversarial attack via perturbation factorization. In: Proceedings of European Conference on Computer Vision (2020)Google Scholar
  20. 20.
    Feng, Y., Wu, B., Fan, Y., Li, Z., Xia, S.: Efficient black-box adversarial attack guided by the distribution of adversarial perturbations. arXiv preprint arXiv:2006.08538 (2020)
  21. 21.
    Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proceedings of International Conference on Learning Representations (2014)Google Scholar
  22. 22.
    Guo, C., Gardner, J.R., You, Y., Wilson, A.G., Weinberger, K.Q.: Simple black-box adversarial attacks. arXiv preprint arXiv:1905.07121 (2019)
  23. 23.
    Guo, Y., Yan, Z., Zhang, C.: Subspace attack: Exploiting promising subspaces for query-efficient black-box attacks. In: Advances in Neural Information Processing Systems, pp. 3825–3834 (2019)Google Scholar
  24. 24.
    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
  25. 25.
    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. 2261–2269 (2017)Google Scholar
  26. 26.
    Huang, G., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report, October 2008Google Scholar
  27. 27.
    Ilyas, A., Engstrom, L., Athalye, A., Lin, J.: Black-box adversarial attacks with limited queries and information. In: Proceedings of International Conference on Machine Learning (2018)Google Scholar
  28. 28.
    Ilyas, A., Engstrom, L., Madry, A.: Prior convictions: black-box adversarial attacks with bandits and priors. In: Proceedings of International Conference on Learning Representations (2019)Google Scholar
  29. 29.
    Krizhevsky, A., et al.: Learning multiple layers of features from tiny images. Technical Report (2009)Google Scholar
  30. 30.
    Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. In: Proceedings of International Conference on Learning Representations (2016)Google Scholar
  31. 31.
    Li, Y., Li, L., Wang, L., Zhang, T., Gong, B.: Nattack: learning the distributions of adversarial examples for an improved black-box attack on deep neural networks. In: Proceedings of International Conference on Machine Learning (2019)Google Scholar
  32. 32.
    Li, Y., et al.: Toward adversarial robustness via semi-supervised robust training. arXiv preprint arXiv:2003.06974 (2020)
  33. 33.
    Li, Y., Yang, X., Wu, B., Lyu, S.: Hiding faces in plain sight: disrupting AI face synthesis with adversarial perturbations. arXiv preprint arXiv:1906.09288 (2019)
  34. 34.
    Liu, Y., Chen, X., Liu, C., Song, D.: Delving into transferable adversarial examples and black-box attacks. In: Proceedings of International Conference on Learning Representations (2016)Google Scholar
  35. 35.
    Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of International Conference on Learning Representations (2017)Google Scholar
  36. 36.
    Moon, S., An, G., Song, H.O.: Parsimonious black-box adversarial attacks via efficient combinatorial optimization. In: Proceedings of International Conference on Machine Learning (2019)Google Scholar
  37. 37.
    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)Google Scholar
  38. 38.
    Papernot, N., McDaniel, P., Goodfellow, I.: Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277 (2016)
  39. 39.
    Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against machine learning. In: Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, pp. 506–519. ACM (2017)Google Scholar
  40. 40.
    Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: Proceedings of the IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)Google Scholar
  41. 41.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  42. 42.
    Suya, F., Chi, J., Evans, D., Tian, Y.: Hybrid batch attacks: finding black-box adversarial examples with limited queries. In: USENIX Security Symposium (2020)Google Scholar
  43. 43.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  44. 44.
    Szegedy, C., et al.: Intriguing properties of neural networks. In: Proceedings of International Conference on Learning Representations (2013)Google Scholar
  45. 45.
    Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., McDaniel, P.: Ensemble adversarial training: attacks and defenses. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  46. 46.
    Wu, D., Wang, Y., Xia, S.T., Bailey, J., Ma, X.: Skip connections matter: on the transferability of adversarial examples generated with resnets. In: Proceedings of International Conference on Learning Representations (2020)Google Scholar
  47. 47.
    Xiao, C., Zhong, P., Zheng, C.: Resisting adversarial attacks by \(k\)-winners-take-all. In: Proceedings of International Conference on Learning Representations (2020)Google Scholar
  48. 48.
    Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., Yuille, A.: Adversarial examples for semantic segmentation and object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1369–1378 (2017)Google Scholar
  49. 49.
    Xie, C., Wu, Y., Maaten, L.V.D., Yuille, A.L., He, K.: Feature denoising for improving adversarial robustness. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  50. 50.
    Xu, W., Evans, D., Qi, Y.: Feature squeezing: detecting adversarial examples in deep neural networks. In: Proceedings of Network and Distributed System Security Symposium. Internet Society (2018)Google Scholar
  51. 51.
    Xu, Y., et al.: Exact adversarial attack to image captioning via structured output learning with latent variables. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4135–4144 (2019)Google Scholar
  52. 52.
    Zhang, H., Wang, J.: Defense against adversarial attacks using feature scattering-based adversarial training. In: Advances in Neural Information Processing Systems (2019)Google Scholar
  53. 53.
    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 International Conference on Machine Learning (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR)Institute of Automation, Chinese Academy of Sciences (CASIA)BeijingChina
  2. 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)BeijingChina
  3. 3.Center for Excellence in Brain Science and Intelligence Technology, CASBeijingChina
  4. 4.Tsinghua UniversityBeijingChina
  5. 5.The Chinese University of Hong KongShenzhenChina
  6. 6.Tencent AI LabShenzhenChina

Personalised recommendations