Visual object tracking is widely adopted to unmanned aerial vehicle (UAV)-related applications, which demand reliable tracking precision and real-time performance. However, UAV trackers are highly susceptible to adversarial attacks, while research on developing effective adversarial defense methods for UAV tracking remains limited. To tackle these challenges, we propose CMDN, a novel pre-processing defense network that effectively purifies adversarial perturbations by reconstructing video frames. This network learns robust visual representations from video frames, guided by meaningful features from both the search region and the template. Comprehensive experiments on three benchmarks demonstrate that CMDN is capable of enhancing a UAV tracker’s adversarial robustness in both adaptive and non-adaptive attack scenarios. In addition, CMDN maintains stable defense effectiveness when transferred to heterogeneous trackers. Real-world tests on the UAV platform also validate its reliable defense effectiveness and real-time performance, with CMDN achieving 27 FPS on NVIDIA Jetson Orin 16 GB (25 W mode).


    Access

    Download


    Export, share and cite



    Title :

    CMDN: Pre-Trained Visual Representations Boost Adversarial Robustness for UAV Tracking


    Contributors:
    Ruilong Yu (author) / Zhewei Wu (author) / Qihe Liu (author) / Shijie Zhou (author) / Min Gou (author) / Bingchen Xiang (author)


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Accumulation of adversarial examples for underwater visual object tracking

    Zhang, Yu / Li, Jin / Zhang, Chenghao | British Library Conference Proceedings | 2022


    Improving VAEs' Robustness to Adversarial Attack

    Willetts, Matthew / Camuto, Alexander / Rainforth, Tom et al. | ArXiv | 2019

    Free access

    CERTIFIED ADVERSARIAL ROBUSTNESS FOR DEEP REINFORCEMENT LEARNING

    LUETJENS BJOERN MALTE / EVERETT MICHAEL F / HOW JONATHAN P et al. | European Patent Office | 2021

    Free access

    Constraining Logits by Bounded Function for Adversarial Robustness

    Kanai, Sekitoshi / Yamada, Masanori / Yamaguchi, Shin'ya et al. | ArXiv | 2020

    Free access

    Assessing the Robustness of Neural Networks Trained for Closed Loop Flow Stabilization

    Oliveira, Tarcísio D. / Wolf, William / Dawson, Scott T. | AIAA | 2024