Version 1
: Received: 17 May 2024 / Approved: 22 May 2024 / Online: 22 May 2024 (13:14:00 CEST)
How to cite:
Ye, P.; Chen, Y.; Ma, S.; Xue, F.; Crespi, N.; Chen, X.; Fang, X. Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models. Preprints2024, 2024051451. https://doi.org/10.20944/preprints202405.1451.v1
Ye, P.; Chen, Y.; Ma, S.; Xue, F.; Crespi, N.; Chen, X.; Fang, X. Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models. Preprints 2024, 2024051451. https://doi.org/10.20944/preprints202405.1451.v1
Ye, P.; Chen, Y.; Ma, S.; Xue, F.; Crespi, N.; Chen, X.; Fang, X. Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models. Preprints2024, 2024051451. https://doi.org/10.20944/preprints202405.1451.v1
APA Style
Ye, P., Chen, Y., Ma, S., Xue, F., Crespi, N., Chen, X., & Fang, X. (2024). Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models. Preprints. https://doi.org/10.20944/preprints202405.1451.v1
Chicago/Turabian Style
Ye, P., Xiaohan Chen and Xing Fang. 2024 "Security in Transformer Visual Trackers: A Case Study on the Adversarial Robustness of Two Models" Preprints. https://doi.org/10.20944/preprints202405.1451.v1
Abstract
Visual object tracking is an important technology in camera based sensor networks, which has a wide range of practicability in auto drive system. A transformer is a deep learning model that adopts the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It makes such transformer-based applications be exposed to security threats. In this work, the security of the transformer model is investigated with the important component of autonomous driving, visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, so adversarial attacks are implemented as the security threats to conduct the investigation. First, adversarial examples are generated on top of video sequences to degrade tracking performance, and the frame-by-frame temporal motion is taken into consideration when generating perturbations over the predicted tracking results. Then, the influence of perturbations on performance is sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrate that the executed adversarial examples are effective on the performance drops of the transformer-based visual tracking.
Keywords
autonomous driving; visual tracking; adversarial attacks; transformer model
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
