Abstract
Despite of achieving remarkable success in computer vision tasks, convolutional neural networks still face the threat of adversarial examples, crafted by adding small human-invisible perturbations on clean inputs. Usually, most of existing black-box adversarial attacks show extremely low transferability while encountering powerful defense models. In this paper, based on the observed invariant property of convolutional neural networks (i.e., the models could maintain accuracy to transformed images), we propose two new methods to improve the transferability which are called as the flip-invariant attack method (FIM) and the brightness-invariant attack method (BIM), respectively. Both the novel approaches derive multiple different logit outputs by inputting the transformed copies of the original image into the white-box model. Simultaneously, the ensemble of these outputs is attacked to avoid overfitting the white-box model and generating more transferable adversarial examples. Moreover, the newly-proposed FIM and BIM methods can be naturally combined with other gradient-based methods. Extensive experiments on the ImageNet dataset prove that our methods achieve higher attack success rate and higher transferability than previous gradient-based attack methods.
Supported by the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant no. KJQN201901101), and the National Natural Science Foundation of China (Grant no. 61603065).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Szegedy, C., et al.: Intriguing properties of neural networks. In: Proceedings of 2nd International Conference on Learning Representations (ICLR 2014) (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of 3rd International Conference on Learning Representations (ICLR 2015) (2015)
Arnab, A., Miksik, O., Torr, P.H.: On the robustness of semantic segmentation models to adversarial attacks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 888–897 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: Proceedings of 3rd International Conference on Learning Representations (ICLR 2015) (2015)
Liu, Y., Chen, X., Liu, C., Song, D.: Delving into transferable adversarial examples and black-box attacks. In: Proceedings of 5th International Conference on Learning Representations (ICLR 2017) (2017)
Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765–1773 (2017)
Liu, W., Zhong, S.: Web malware spread modelling and optimal control strategies. Sci. Rep. 7, (2017) Article no. 42308
Liu, W., Zhong, S.: Modeling and analyzing the dynamic spreading of epidemic malware by a network eigenvalue method. Appl. Math. Model. 63, 491–507 (2018)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. In: Proceedings of 5th International Conference on Learning Representations (ICLR 2017) (2017)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: Proceedings of the IEEE Symposium on Security and Privacy, pp. 39–57 (2017)
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)
Xie, C., et al.: Improving transferability of adversarial examples with input diversity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2730–2739 (2019)
Dong, Y., Pang, T., Su, H., Zhu, J.: Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4312–4321 (2019)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Tramer, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., McDaniel, P.: Ensemble adversarial training: attacks and defenses. In: Proceedings of 6th International Conference on Learning Representations (ICLR 2018) (2018)
Guo, C., Rana, M., Cisse, M., Van Der Maaten, L.: Countering adversarial images using input transformations. In: Proceedings of 6th International Conference on Learning Representations (ICLR 2018) (2018)
Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. In: Proceedings of 6th International Conference on Learning Representations (ICLR 2018) (2018)
Liu, Z., et al.: Feature distillation: DNN-oriented jpeg compression against adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 860–868 (2019)
Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.: Defense against adversarial attacks using high-level representation guided denoiser. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1778–1787 (2018)
Jia, X., Wei, X., Cao, X., Foroosh, H.: Comdefend: an efficient image compression model to defend adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6084–6092 (2019)
Cohen, J.M., Rosenfeld, E., Kolter, J.Z.: Certified adversarial robustness via randomized smoothing. In: Proceedings of 7th International Conference on Learning Representations (ICLR 2019) (2019)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of 6th International Conference on Learning Representations (ICLR 2018) (2018)
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)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence, pp. 4278–4284 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A: Details of the Algorithms
Appendix A: Details of the Algorithms
The algorithm of FI-BI-TI-DIM attack is summarized in Algorithm 2.
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, W., Li, Z. (2020). Enhancing Adversarial Examples with Flip-Invariance and Brightness-Invariance. In: Yu, S., Mueller, P., Qian, J. (eds) Security and Privacy in Digital Economy. SPDE 2020. Communications in Computer and Information Science, vol 1268. Springer, Singapore. https://doi.org/10.1007/978-981-15-9129-7_32
Download citation
DOI: https://doi.org/10.1007/978-981-15-9129-7_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9128-0
Online ISBN: 978-981-15-9129-7
eBook Packages: Computer ScienceComputer Science (R0)