STA: Adversarial Attacks on Siamese Trackers

Recently, the majority of visual trackers adopt Convolutional Neural Network (CNN) as their backbone to achieve high tracking accuracy. However, less attention has been paid to the potential adversarial threats brought by CNN, including Siamese network. In this paper, we first analyze the existing vulnerabilities in Siamese trackers and propose the requirements for a successful adversarial attack. On this basis, we formulate the adversarial generation problem and propose an end-to-end pipeline to generate a perturbed texture map for the 3D object that causes the trackers to fail. Finally, we conduct thorough experiments to verify the effectiveness of our algorithm. Experiment results show that adversarial examples generated by our algorithm can successfully lower the tracking accuracy of victim trackers and even make them drift off. To the best of our knowledge, this is the first work to generate 3D adversarial examples on visual trackers.

[1]  Hassan Foroosh,et al.  CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild , 2018, ICLR.

[2]  Louis B. Rall,et al.  Automatic differentiation , 1981 .

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Dawn Xiaodong Song,et al.  Delving into Transferable Adversarial Examples and Black-box Attacks , 2016, ICLR.

[5]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[6]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[7]  Michael Felsberg,et al.  The Sixth Visual Object Tracking VOT2018 Challenge Results , 2018, ECCV Workshops.

[8]  Wei Wu,et al.  High Performance Visual Tracking with Siamese Region Proposal Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Logan Engstrom,et al.  Synthesizing Robust Adversarial Examples , 2017, ICML.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Yuhong Li,et al.  SiamVGG: Visual Tracking using Deeper Siamese Networks , 2019, ArXiv.

[12]  Chong Luo,et al.  A Twofold Siamese Network for Real-Time Object Tracking , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Philip H. S. Torr,et al.  On the Robustness of Semantic Segmentation Models to Adversarial Attacks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[15]  Arnold W. M. Smeulders,et al.  UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking , 2016 .

[16]  Wei Wu,et al.  Distractor-aware Siamese Networks for Visual Object Tracking , 2018, ECCV.

[17]  Luca Bertinetto,et al.  End-to-End Representation Learning for Correlation Filter Based Tracking , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Alan L. Yuille,et al.  Adversarial Examples for Semantic Segmentation and Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Atul Prakash,et al.  Robust Physical-World Attacks on Deep Learning Visual Classification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Silvio Savarese,et al.  Learning to Track at 100 FPS with Deep Regression Networks , 2016, ECCV.

[21]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[22]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Tatsuya Harada,et al.  Neural 3D Mesh Renderer , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Seyed-Mohsen Moosavi-Dezfooli,et al.  Universal Adversarial Perturbations , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[26]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[27]  Duen Horng Chau,et al.  ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector , 2018, ECML/PKDD.

[28]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.