Skip to main content

Adversarially-Aware Robust Object Detector

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13669))

Included in the following conference series:

Abstract

Object detection, as a fundamental computer vision task, has achieved a remarkable progress with the emergence of deep neural networks. Nevertheless, few works explore the adversarial robustness of object detectors to resist adversarial attacks for practical applications in various real-world scenarios. Detectors have been greatly challenged by unnoticeable perturbation, with sharp performance drop on clean images and extremely poor performance on adversarial images. In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images. To mitigate this issue, we propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. RobustDet also employs the Adversarial Image Discriminator (AID) and Consistent Features with Reconstruction (CFR) to ensure a reliable robustness. Extensive experiments on PASCAL VOC and MS-COCO demonstrate that our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images. Our source code and trained models are publicly available at: https://github.com/7eu7d7/RobustDet.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Benz, P., Zhang, C., Kweon, I.S.: Batch normalization increases adversarial vulnerability and decreases adversarial transferability: a non-robust feature perspective. In: International Conference on Computer Vision (ICCV), pp. 7818–7827 (2021)

    Google Scholar 

  2. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  3. Carlini, N., Wagner, D.A.: Towards evaluating the robustness of neural networks. In: IEEE Symposium on Security and Privacy, pp. 39–57 (2017)

    Google Scholar 

  4. Chen, L., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision (ECCV), pp. 833–851 (2018)

    Google Scholar 

  5. Chen, P., Kung, B., Chen, J.: Class-aware robust adversarial training for object detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 10420–10429 (2021)

    Google Scholar 

  6. Chen, S.-T., Cornelius, C., Martin, J., Chau, D.H.P.: ShapeShifter: robust physical adversarial attack on faster R-CNN object detector. In: Berlingerio, M., Bonchi, F., Gärtner, T., Hurley, N., Ifrim, G. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11051, pp. 52–68. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-10925-7_4

    Chapter  Google Scholar 

  7. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: Computer Vision and Pattern Recognition (CVPR), pp. 11027–11036 (2020)

    Google Scholar 

  8. Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2014). https://doi.org/10.1007/s11263-014-0733-5

    Article  Google Scholar 

  9. Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)

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

    Google Scholar 

  11. Gowal, S., Rebuffi, S., Wiles, O., Stimberg, F., Calian, D.A., Mann, T.: Improving robustness using generated data. CoRR abs/2110.09468 (2021)

    Google Scholar 

  12. 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 

  13. Howard, A., et al.: Searching for mobilenetv3. In: International Conference on Computer Vision (ICCV), pp. 1314–1324 (2019)

    Google Scholar 

  14. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

  15. Liang, S., Wu, B., Fan, Y., Wei, X., Cao, X.: Parallel rectangle flip attack: a query-based black-box attack against object detection. In: International Conference on Computer Vision (ICCV), pp. 7697–7707 (2021)

    Google Scholar 

  16. Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.: Defense against adversarial attacks using high-level representation guided denoiser. In: Computer Vision and Pattern Recognition (CVPR), pp. 1778–1787 (2018)

    Google Scholar 

  17. Lin, J.: Divergence measures based on the shannon entropy. IEEE Trans. Inf. Theor. 37(1), 145–151 (1991)

    Article  MathSciNet  MATH  Google Scholar 

  18. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  19. Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  20. Liu, X., Yang, H., Liu, Z., Song, L., Chen, Y., Li, H.: DPATCH: an adversarial patch attack on object detectors. In: Workshop on Thirty-Third AAAI Conference on Artificial Intelligence (AAAI) (2019)

    Google Scholar 

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

    Google Scholar 

  22. Qin, C., et al.: Adversarial robustness through local linearization. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 13824–13833 (2019)

    Google Scholar 

  23. Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 91–99 (2015)

    Google Scholar 

  24. Sarkar, S., Bansal, A., Mahbub, U., Chellappa, R.: UPSET and ANGRI : breaking high performance image classifiers. CoRR abs/1707.01159 (2017)

    Google Scholar 

  25. Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Computer Vision and Pattern Recognition (CVPR), pp. 815–823 (2015)

    Google Scholar 

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

    Google Scholar 

  27. Su, J., Vargas, D.V., Sakurai, K.: One pixel attack for fooling deep neural networks. IEEE Trans. Evol. Comput. 23(5), 828–841 (2019)

    Article  Google Scholar 

  28. Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

  29. Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I.J., Boneh, D., McDaniel, P.D.: Ensemble adversarial training: attacks and defenses. In: International Conference on Learning Representations (ICLR) (2018)

    Google Scholar 

  30. Wei, X., Liang, S., Chen, N., Cao, X.: Transferable adversarial attacks for image and video object detection. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 954–960 (2019)

    Google Scholar 

  31. Xiao, C., Li, B., Zhu, J., He, W., Liu, M., Song, D.: Generating adversarial examples with adversarial networks. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 3905–3911 (2018)

    Google Scholar 

  32. Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., Yuille, A.L.: Adversarial examples for semantic segmentation and object detection. In: International Conference on Computer Vision (ICCV), pp. 1378–1387 (2017)

    Google Scholar 

  33. Yang, J., Jiang, Y., Huang, X., Ni, B., Zhao, C.: Learning black-box attackers with transferable priors and query feedback. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)

    Google Scholar 

  34. Zhang, H., Wang, J.: Towards adversarially robust object detection. In: International Conference on Computer Vision (ICCV), pp. 421–430 (2019)

    Google Scholar 

  35. Zhang, H., Yu, Y., Jiao, J., Xing, E.P., Ghaoui, L.E., Jordan, M.I.: Theoretically principled trade-off between robustness and accuracy. In: International Conference on Machine Learning (ICML), pp. 7472–7482 (2019)

    Google Scholar 

  36. Zhang, J., et al.: Attacks which do not kill training make adversarial learning stronger. In: International Conference on Machine Learning (ICML), pp. 11278–11287 (2020)

    Google Scholar 

  37. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230–6239 (2017)

    Google Scholar 

Download references

Acknowledgement

This work was supported in part by NSFC (No. 62006253, U21A20470, 61876224), National Key R &D Program of China (2021ZD0111601).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Pengxu Wei .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2288 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dong, Z., Wei, P., Lin, L. (2022). Adversarially-Aware Robust Object Detector. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13669. Springer, Cham. https://doi.org/10.1007/978-3-031-20077-9_18

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20077-9_18

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20076-2

  • Online ISBN: 978-3-031-20077-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics