Skip to main content
SpringerLink
Log in

Transferable adversarial sample purification by expanding the purification space of diffusion models

  • Research
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial samples and many powerful defense methods have been proposed to enhance the adversarial robustness of DNNs. However, these defenses often require adding regularization terms to the loss function or augmenting the training data, which often involves modification of the target model and increases computational consumption. In this paper, we propose a novel adversarial defense approach that leverages the diffusion model with a large purification space to purify potential adversarial samples, and introduce two training strategies termed PSPG and PDPG to defend against different attacks. Our method preprocesses adversarial examples before they are inputted into the target model, and thus can provide protection for DNNs in the inference phase. It does not require modifications to the target model and can protect even deployed models. Extensive experiments on CIFAR-10 and ImageNet demonstrate that our method has good accuracy and transferability, it can provide protection effectively for different models in various defense scenarios. Our code is available at: https://github.com/YNU-JI/PDPG.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Algorithm 1
Algorithm 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Li, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Inform. 18(1), 163–173 (2022). https://doi.org/10.1109/TII.2021.3085669

    Article  CAS  Google Scholar 

  2. Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: Bagfn: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499–4513 (2023). https://doi.org/10.1109/TNNLS.2021.3116209

    Article  PubMed  Google Scholar 

  3. Sheng, B., Li, P., Ali, R., Chen, C.L.P.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662–6675 (2022). https://doi.org/10.1109/TCYB.2021.3079311

    Article  PubMed  Google Scholar 

  4. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations (2015)

  5. Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: 5th International Conference on Learning Representations (2017)

  6. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: 6th International Conference on Learning Representations (2018)

  7. Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., Li, J.: Boosting adversarial attacks with momentum. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185–9193 (2018). https://doi.org/10.1109/CVPR.2018.00957

  8. Moosavi-Dezfooli, S., Fawzi, A., Frossard, P.: Deepfool: A simple and accurate method to fool deep neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016). https://doi.org/10.1109/CVPR.2016.282

  9. Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy, pp. 39–57 (2017). https://doi.org/10.1109/SP.2017.49

  10. Xie, C., Wu, Y., Maaten, L., Yuille, A.L., He, K.: Feature denoising for improving adversarial robustness. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 501–509 (2019). https://doi.org/10.1109/CVPR.2019.00059

  11. Song, C., He, K., Lin, J., Wang, L., Hopcroft, J.E.: Robust local features for improving the generalization of adversarial training. In: 8th International Conference on Learning Representations (2020)

  12. Papernot, N., McDaniel, P.D., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: IEEE Symposium on Security and Privacy, pp. 582–597 (2016). https://doi.org/10.1109/SP.2016.41

  13. Ross, A.S., Doshi-Velez, F.: Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, pp. 1660–1669 (2018). https://doi.org/10.1609/AAAI.V32I1.11504

  14. Dziugaite, G.K., Ghahramani, Z., Roy, D.M.: A study of the effect of JPG compression on adversarial images (2016). arXiv preprint arXiv:1608.00853

  15. Guo, C., Rana, M., Cissé, M., Maaten, L.: Countering adversarial images using input transformations. In: 6th International Conference on Learning Representations (2018)

  16. Gu, S., Rigazio, L.: Towards deep neural network architectures robust to adversarial examples. In: 3rd International Conference on Learning Representations (2015)

  17. Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.: Defense against adversarial attacks using high-level representation guided denoiser. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1778–1787 (2018). https://doi.org/10.1109/CVPR.2018.00191

  18. Gao, S., Yao, S., Li, R.: Transferable adversarial defense by fusing reconstruction learning and denoising learning. In: IEEE Conference on Computer Communications Workshops, pp. 1–6 (2021). https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484542

  19. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840–6851 (2020)

    Google Scholar 

  20. Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 8162–8171 (2021)

  21. Bansal, A., Borgnia, E., Chu, H., Li, J.S., Kazemi, H., Huang, F., Goldblum, M., Geiping, J., Goldstein, T.: Cold diffusion: inverting arbitrary image transforms without noise. arXiv preprint arXiv:2208.09392

  22. Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4195–4205 (2023)

  23. Cheng, S., Chen, Y., Chiu, W., Tseng, H., Lee, H.: Adaptively-realistic image generation from stroke and sketch with diffusion model. In: IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 4043–4051 (2023). https://doi.org/10.1109/WACV56688.2023.00404

  24. Kawar, B., Song, J., Ermon, S., Elad, M.: JPEG artifact correction using denoising diffusion restoration models. In: NeurIPS 2022 Workshop on Score-Based Methods (2022)

  25. Saharia, C., Chan, W., Chang, H., Lee, C.A., Ho, J., Salimans, T., Fleet, D.J., Norouzi, M.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1–10 (2022). https://doi.org/10.1145/3528233.3530757

  26. Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713–4726 (2023). https://doi.org/10.1109/TPAMI.2022.3204461

    Article  PubMed  Google Scholar 

  27. Jiang, N., Sheng, B., Li, P., Lee, T.: Photohelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multimed. 25, 2226–2238 (2023). https://doi.org/10.1109/TMM.2022.3144890

    Article  Google Scholar 

  28. Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50–61 (2023). https://doi.org/10.1109/TMM.2021.3120873

    Article  Google Scholar 

  29. Chen, Z., Qiu, G., Li, P., Zhu, L., Yang, X., Sheng, B.: MNGNAS: distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13489–13508 (2023). https://doi.org/10.1109/TPAMI.2023.3293885

    Article  PubMed  Google Scholar 

  30. 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, vol. 119, pp. 2206–2216 (2020)

  31. Papernot, N., McDaniel, P.D., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: IEEE European Symposium on Security and Privacy, pp. 372–387 (2016). https://doi.org/10.1109/EUROSP.2016.36

  32. Moosavi-Dezfooli, S., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21–26, 2017, pp. 86–94 (2017). https://doi.org/10.1109/CVPR.2017.17

  33. Bhattad, A., Chong, M.J., Liang, K., Li, B., Forsyth, D.A.: Unrestricted adversarial examples via semantic manipulation. In: 8th International Conference on Learning Representations (2020)

  34. Shamsabadi, A.S., Sánchez-Matilla, R., Cavallaro, A.: Colorfool: semantic adversarial colorization. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1148–1157 (2020). https://doi.org/10.1109/CVPR42600.2020.00123

  35. Zhao, Z., Liu, Z., Larson, M.A.: Adversarial color enhancement: generating unrestricted adversarial images by optimizing a color filter. In: 31st British Machine Vision Conference 2020 (2020)

  36. Yuan, S., Zhang, Q., Gao, L., Cheng, Y., Song, J.: Natural color fool: towards boosting black-box unrestricted attacks. Adv. Neural Inf. Process. Syst. 35, 7546–7560 (2022)

    Google Scholar 

  37. Chen, J., Chen, H., Chen, K., Zhang, Y., Zou, Z., Shi, Z.: Diffusion models for imperceptible and transferable adversarial attack (2023). arXiv preprint arXiv:2305.08192

  38. Zheng, S., Song, Y., Leung, T., Goodfellow, I.J.: Improving the robustness of deep neural networks via stability training. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4480–4488 (2016). https://doi.org/10.1109/CVPR.2016.485

  39. Ye, N., Li, Q., Zhou, X., Zhu, Z.: Amata: An annealing mechanism for adversarial training acceleration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10691–10699 (2021). https://doi.org/10.1609/AAAI.V35I12.17278

  40. Gokhale, T., Anirudh, R., Kailkhura, B., Thiagarajan, J.J., Baral, C., Yang, Y.: Attribute-guided adversarial training for robustness to natural perturbations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 7574–7582 (2021). https://doi.org/10.1609/AAAI.V35I9.16927

  41. Terzi, M., Achille, A., Maggipinto, M., Susto, G.A.: Adversarial training reduces information and improves transferability. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2674–2682. https://doi.org/10.1609/AAAI.V35I3.16371

  42. Metzen, J.H., Genewein, T., Fischer, V., Bischoff, B.: On detecting adversarial perturbations. In: 5th International Conference on Learning Representations (2017)

  43. Xu, W., Evans, D., Qi, Y.: Feature squeezing: Detecting adversarial examples in deep neural networks. In: 25th Annual Network and Distributed System Security Symposium (2018)

  44. Pang, T., Du, C., Dong, Y., Zhu, J.: Towards robust detection of adversarial examples. Adv. Neural Inf. Process. Syst. 31, 25 (2018)

    Google Scholar 

  45. Zheng, Z., Hong, P.: Robust detection of adversarial attacks by modeling the intrinsic properties of deep neural networks. Adv. Neural Inf. Process. Syst. 31, 25 (2018)

    Google Scholar 

  46. Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., Chan, W.: Wavegrad: estimating gradients for waveform generation. In: 9th International Conference on Learning Representations (2021)

  47. Chattopadhyay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 839–847 (2018). https://doi.org/10.1109/WACV.2018.00097

  48. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90

  49. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (2015)

  50. Huang, G., Liu, Z., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243

  51. Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A.C., Li, Y.: Maxvit: multi-axis vision transformer. In: European Conference on Computer Vision, vol. 13684, pp. 459–479 (2022). https://doi.org/10.1007/978-3-031-20053-3_27

  52. Hill, M., Mitchell, J.C., Zhu, S.: Stochastic security: adversarial defense using long-run dynamics of energy-based models. In: 9th International Conference on Learning Representations (2021)

Download references

Acknowledgements

This paper was supported by the National Natural Science Foundation of China under Grant 62162067 and 62101480.

Author information

Authors and Affiliations

  1. School of Software, Yunnan University, Kunming, 650504, China

    Jun Ji, Song Gao & Wei Zhou

Authors
  1. Jun Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Song Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JJ: Methodology, Software, Conceptualization, Writing original draft. SG: Methodology, Software, Investigation, Writing review. WZ: Supervision, Funding acquisition.

Corresponding author

Correspondence to Song Gao.

Ethics declarations

Conflicts of interest

We declare that there is no conflict of interest related to the content of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ji, J., Gao, S. & Zhou, W. Transferable adversarial sample purification by expanding the purification space of diffusion models. Vis Comput (2024). https://doi.org/10.1007/s00371-023-03253-7

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00371-023-03253-7

Keywords

Search

Navigation