Abstract
In recent years, Siamese networks have led to great progress in visual object tracking. While these methods were shown to be vulnerable to adversarial attacks, the existing attack strategies do not truly pose great practical threats. They either are too expensive to be performed online, require computing image-dependent perturbations, lead to unrealistic trajectories, or suffer from weak transferability to other black-box trackers. In this paper, we address the above limitations by showing the existence of a universal perturbation that is image agnostic and fools black-box trackers at virtually no cost of perturbation. Furthermore, we show that our framework can be extended to the challenging targeted attack setting that forces the tracker to follow any given trajectory by using diverse directional universal perturbations. At the core of our framework, we propose to learn to generate a single perturbation from the object template only, that can be added to every search image and still successfully fool the tracker for the entire video. As a consequence, the resulting generator outputs perturbations that are quasi-independent of the template, thereby making them universal perturbations. Our extensive experiments on four benchmarks datasets, i.e., OTB100, VOT2019, UAV123, and LaSOT, demonstrate that our universal transferable perturbations (computed on SiamRPN++) are highly effective when transferred to other state-of-the-art trackers, such as SiamBAN, SiamCAR, DiMP, and Ocean online.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Ban, Y., Ba, S., Alameda-Pineda, X., Horaud, R.: Tracking multiple persons based on a variational Bayesian model. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 52–67. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_5
Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6182–6191 (2019)
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2544–2550. IEEE (2010)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)
Chen, X., et al.: One-shot adversarial attacks on visual tracking with dual attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10176–10185 (2020)
Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R.: Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6668–6677 (2020)
Danelljan, M., Hager, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4310–4318 (2015)
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)
Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374–5383 (2019)
Fischer, V., Kumar, M.C., Metzen, J.H., Brox, T.: Adversarial examples for semantic image segmentation. arXiv preprint arXiv:1703.01101 (2017)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Guo, D., Wang, J., Cui, Y., Wang, Z., Chen, S.: SiamCAR: siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6269–6277 (2020)
Guo, Q., et al.: SPARK: spatial-aware online incremental attack against visual tracking. arXiv preprint arXiv:1910.08681 (2019)
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)
Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562–1577 (2019)
Jia, S., Song, Y., Ma, C., Yang, X.: IoU attack: towards temporally coherent black-box adversarial attack for visual object tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6709–6718 (2021)
Jia, Y., Lu, Y., Shen, J., Chen, Q.A., Zhong, Z., Wei, T.: Fooling detection alone is not enough: first adversarial attack against multiple object tracking. arXiv preprint arXiv:1905.11026 (2019)
Kiani Galoogahi, H., Sim, T., Lucey, S.: Multi-channel correlation filters. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3072–3079 (2013)
Kiani Galoogahi, H., Sim, T., Lucey, S.: Correlation filters with limited boundaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4630–4638 (2015)
Kristan, M., et al.: The sixth visual object tracking VOT2018 challenge results. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 3–53. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11009-3_1
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Lee, K.H., Hwang, J.N.: On-road pedestrian tracking across multiple driving recorders. IEEE Trans. Multimed. 17(9), 1429–1438 (2015)
Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4282–4291 (2019)
Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971–8980 (2018)
Liang, S., Wei, X., Yao, S., Cao, X.: Efficient adversarial attacks for visual object tracking. arXiv preprint arXiv:2008.00217 (2020)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (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)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: DeepFool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016)
Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445–461. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_27
Poursaeed, O., Katsman, I., Gao, B., Belongie, S.: Generative adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4422–4431 (2018)
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 (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1328–1338 (2019)
Wiyatno, R.R., Xu, A.: Physical adversarial textures that fool visual object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4822–4831 (2019)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411–2418 (2013)
Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., Song, D.: Generating adversarial examples with adversarial networks. arXiv preprint arXiv:1801.02610 (2018)
Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., Yuille, A.: Adversarial examples for semantic segmentation and object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1369–1378 (2017)
Yan, B., Wang, D., Lu, H., Yang, X.: Cooling-shrinking attack: blinding the tracker with imperceptible noises. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 990–999 (2020)
Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 771–787. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_46
Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103–119. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_7
Acknowledgments
This work was funded in part by the Swiss National Science Foundation.
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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nakka, K.K., Salzmann, M. (2023). Universal, Transferable Adversarial Perturbations for Visual Object Trackers. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13801. Springer, Cham. https://doi.org/10.1007/978-3-031-25056-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-25056-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25055-2
Online ISBN: 978-3-031-25056-9
eBook Packages: Computer ScienceComputer Science (R0)