Abstract
In recent years, adversarial examples have played a significant role in protecting image privacy and improving the robustness of deep learning models. Most adversarial example generations are conducted in uncompressed domain; however, most images are compressed in storage and network transmission, and the compression definitely degrades the adversarial effectiveness. Absolute moment block truncation coding (AMBTC) is popular for image compression. This paper aims to study the adversarial face example generation for AMBTC format. The method is proposed and optimized in compressed trio-data domain (CTD), the adversarial face example generation is optimized directly on the trio data of each block rather than on each pix. Since CTD method optimizes the trio data, it reduces the computational overhead. The experiments on LFW face database confirm that CTD method has satisfactory anti-compression ability for AMBTC format, and simultaneously has satisfactory image quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Guo, C., Rana, M., Cisse, M., Van, D.M.L.: Countering adversarial images using input transformations. arXiv preprint arXiv:1711.00117 (2017)
Jia, X., Wei, X., Cao X., Foroosh H.: ComDefend: an efficient image compression model to defend adversarial examples. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6084–6092 (2019)
Kim, C., Shin, D., Yang, C., Leng, L.: Data hiding method for color AMBTC compressed images using color difference. Appl. Sci. 11, 3418 (2021)
Kim, C., Shin, D., Yang, C.N., Leng L.: Hybrid data hiding based on AMBTC using enhanced hamming code. Appl. Sci. 10, 5336 (2020)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2014)
Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Shin, R., Song, D.: Jpeg-resistant adversarial images. In: NIPS 2017 Workshop on Machine Learning and Computer Security, pp. 1–8 (2017)
Wang, Z., et al.: Towards compression-resistant privacy-preserving photo sharing on social networks. In: Proceedings of the 21th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, pp. 81–90 (2020)
Shi, M., Li, S., Yin, Z., Zhang, X., Qian, Z.: On generating JPEG adversarial images. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2021)
Sharma, Y., Ding, G., Brubaker, M.: On the effectiveness of low frequency perturbations. arXiv preprint arXiv:1903.00073 (2019)
Duan, R., Chen, Y., Niu, D., Yang, Y., Qin, A.K., He, Y.: AdvDrop: adversarial attack to DNNs by dropping information. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR), pp. 7506–7515 (2021)
Zhou, W., et al.: Transferable adversarial perturbations. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 452–467 (2018)
Zhang, J., Yi, Q., Sang J., Sang, J.: JPEG compression-resistant low-mid adversarial perturbation against unauthorized face recognition system. arXiv preprint arXiv:2206.09410 (2022)
Lema, M., Mitchell, O.: Absolute moment block truncation coding and its application to color images. IEEE Trans. Commun. 32, 1148–1157 (1984)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4690–4699 (2019)
Duta, I.C., Liu, L., Zhu, F.: Improved residual networks for image and video recognition. In 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9415–9422. IEEE (2021)
Acknowledgments
This research was supported by the National Natural Science Foundation of China (61866028) and (62376003), the Technology Innovation Guidance Program Project (Special Project of Technology Cooperation, Science and Technology Department of Jiangxi Province) (20212BDH81003).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lou, R., Leng, L., Wang, H., Jin, Z. (2023). Adversarial Face Example Generation in AMBTC Compressed Domain. In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_20
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)