Abstract
By adding human-imperceptible noise to clean images, the resultant adversarial examples can fool other unknown models. Features of a pixel extracted by deep neural networks (DNNs) are influenced by its surrounding regions, and different DNNs generally focus on different discriminative regions in recognition. Motivated by this, we propose a patch-wise iterative algorithm – a black-box attack towards mainstream normally trained and defense models, which differs from the existing attack methods manipulating pixel-wise noise. In this way, without sacrificing the performance of white-box attack, our adversarial examples can have strong transferability. Specifically, we introduce an amplification factor to the step size in each iteration, and one pixel’s overall gradient overflowing the \(\epsilon \)-constraint is properly assigned to its surrounding regions by a project kernel. Our method can be generally integrated to any gradient-based attack methods. Compared with the current state-of-the-art attacks, we significantly improve the success rate by 9.2% for defense models and 3.7% for normally trained models on average. Our code is available at https://github.com/qilong-zhang/Patch-wise-iterative-attack
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Pixel values of a valid image are in [0, 255]. If the values are more than 255, they will be modified into 0 for “uint8” type, to give better contrast.
- 2.
- 3.
Input size need to be [224,224,3], therefore we need resize adversarial examples whose size is [299,299,3].
References
Cissé, M., Adi, Y., Neverova, N., Keshet, J.: Houdini: fooling deep structured prediction models. CoRR abs/1707.05373 (2017)
Dong, Y., et al.: Boosting adversarial attacks with momentum. In: CVPR (2018)
Dong, Y., Pang, T., Su, H., Zhu, J.: Evading defenses to transferable adversarial examples by translation-invariant attacks. In: CVPR (2019)
Dziugaite, G.K., Ghahramani, Z., Roy, D.M.: A study of the effect of JPG compression on adversarial images. CoRR abs/1608.00853 (2016)
Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: SIGGRAPH (2001)
Eykholt, K., et al.: Robust physical-world attacks on deep learning visual classification. In: CVPR (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)
Guo, C., Rana, M., Cissé, M., van der Maaten, L.: Countering adversarial images using input transformations. In: ICLR (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)
Ilyas, A., Engstrom, L., Athalye, A., Lin, J.: Black-box adversarial attacks with limited queries and information. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML (2018)
Komkov, S., Petiushko, A.: AdvHat: real-world adversarial attack on ArcFace face ID system. CoRR abs/1908.08705 (2019)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: ICLR (2017)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial machine learning at scale. In: ICLR (2017)
Li, X., et al.: Learnable aggregating net with diversity learning for video question answering. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1166–1174 (2019)
Li, X., et al.: Beyond RNNs: positional self-attention with co-attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8658–8665 (2019)
Li, Y., Bai, S., Xie, C., Liao, Z., Shen, X., Yuille, A.L.: Regional homogeneity: towards learning transferable universal adversarial perturbations against defenses. CoRR abs/1904.00979 (2019)
Lin, J., Gan, C., Han, S.: Defensive quantization: when efficiency meets robustness. In: ICLR (2019)
Liu, A., et al.: Spatiotemporal attacks for embodied agents. In: ECCV (2020)
Liu, A., Wang, J., Liu, X., Cao, b., Zhang, C., Yu, H.: Bias-based universal adversarial patch attack for automatic check-out. In: ECCV (2020)
Liu, Y., Chen, X., Liu, C., Song, D.: Delving into transferable adversarial examples and black-box attacks. In: ICLR (2017)
Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: CVPR (2015)
Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: CVPR (2017)
Papernot, N., McDaniel, P.D., Goodfellow, I.J., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against machine learning. In: Karri, R., Sinanoglu, O., Sadeghi, A., Yi, X. (eds.) AsiaCCS (2017)
Rosen, J.: The gradient projection method for nonlinear programming. Part I. Linear constraints. J. Soc. Ind. Appl. Math. 8, 181–217 (1960)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenom. 60(1-4), 259–268 (1992)
Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. CoRR abs/1703.03864 (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: ICCV (2017)
Sharif, M., Bhagavatula, S., Bauer, L., Reiter, M.K.: Accessorize to a crime: real and stealthy attacks on state-of-the-art face recognition. In: SIGSAC (2016)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)
Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR (2014)
Thys, S., Ranst, W.V., Goedemé, T.: Fooling automated surveillance cameras: adversarial patches to attack person detection. In: CVPR Workshops (2019)
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I.J., Boneh, D., McDaniel, P.D.: Ensemble adversarial training: attacks and defenses. In: ICLR (2018)
Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., Yuille, A.L.: Adversarial examples for semantic segmentation and object detection. In: ICCV (2017)
Xie, C., Wu, Y., van der Maaten, L., Yuille, A.L., He, K.: Feature denoising for improving adversarial robustness. In: CVPR (2019)
Xie, C., et al.: Improving transferability of adversarial examples with input diversity. In: CVPR (2019)
Xu, K., et al.: Interpreting adversarial examples by activation promotion and suppression. CoRR abs/1904.02057 (2019)
Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)
Acknowledgments
This work is supported by the Fundamental Research Funds for the Central Universities (Grant No. ZYGX2019J073), the National Natural Science Foundation of China (Grant No. 61772116, No. 61872064, No. 61632007, No. 61602049), The Open Project of Zhejiang Lab (Grant No. 2019KD0AB05).
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, L., Zhang, Q., Song, J., Liu, X., Shen, H.T. (2020). Patch-Wise Attack for Fooling Deep Neural Network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12373. Springer, Cham. https://doi.org/10.1007/978-3-030-58604-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-58604-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58603-4
Online ISBN: 978-3-030-58604-1
eBook Packages: Computer ScienceComputer Science (R0)