Skip to main content

EFFICIENT UNIVERSAL SHUFFLE ATTACK FOR VISUAL OBJECT TRACKING

Siao Liu, Zhaoyu Chen, Wei Li, Jiwei Zhu, Jiafeng Wang, Wenqiang Zhang, Zhongxue Gan

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:08:07
12 May 2022

Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames. However, previous work only generates the video-specific perturbations, which restricts its application scenarios. In addition, existing attacks are difficult to implement in reality due to the real-time of tracking and the re-initialization mechanism. To address these issues, we propose an offline universal adversarial attack called Efficient Universal Shuffle Attack. It takes only one perturbation to cause the tracker malfunction on all videos. To improve the computational efficiency and attack performance, we propose a greedy gradient strategy and a triple loss to efficiently capture and attack model-specific feature representations through the gradients. Experimental results show that EUSA can significantly reduce the performance of state-of-the-art trackers on OTB2015 and VOT2018.

More Like This

01 Feb 2024

P4.16-Adversarial Examples

1.00 pdh 0.10 ceu
  • SPS
    Members: Free
    IEEE Members: Free
    Non-members: Free
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00