A Unified Multi-Scenario Attacking Network for Visual Object Tracking

Authors

  • Xuesong Chen The Chinese University of Hong Kong
  • Canmiao Fu Tencent
  • Feng Zheng SUSTech
  • Yong Zhao Peking University Shenzhen Graduate School
  • Hongsheng Li Chinese University of Hong Kong
  • Ping Luo The University of Hong Kong
  • Guo-Jun Qi Futurewei Technologies

Keywords:

Adversarial Attacks & Robustness, Motion & Tracking

Abstract

Existing methods of adversarial attacks successfully generate adversarial examples to confuse Deep Neural Networks (DNNs) of image classification and object detection, resulting in wrong predictions. However, these methods are difficult to attack models of video object tracking, because the tracking algorithms could handle sequential information across video frames and the categories of targets tracked are normally unknown in advance. In this paper, we propose a Unified and Effective Network, named UEN, to attack visual object tracking models. There are several appealing characteristics of UEN: (1) UEN could produce various invisible adversarial perturbations according to different attack settings by using only one simple end-to-end network with three ingenious loss function; (2) UEN could generate general visible adversarial patch patterns to attack the advanced trackers in the real-world; (3) Extensive experiments show that UEN is able to attack many state-of-the-art trackers effectively (e.g. SiamRPN-based networks and DiMP) on popular tracking datasets including OTB100, UAV123, and GOT10K, making online real-time attacks possible. The attack results outperform the introduced baseline in terms of attacking ability and attacking efficiency.

Downloads

Published

2021-05-18

How to Cite

Chen, X., Fu, C., Zheng, F., Zhao, Y., Li, H., Luo, P., & Qi, G.-J. (2021). A Unified Multi-Scenario Attacking Network for Visual Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1097-1104. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16195

Issue

Section

AAAI Technical Track on Computer Vision I