Significant advancements in robustness against input perturbations have been realized for deep neural networks (DNNs) through the application of adversarial training techniques. However, implementing these methods for perception tasks in unmanned vehicles, such as object detection and semantic segmentation, particularly on real-time single-board computing devices, encounters two primary challenges: the time-intensive nature of training large-scale models and performance degradation due to weight quantization in real-time deployments. To address these challenges, we propose Ca-PAT, an efficient and effective adversarial training framework designed to mitigate perturbations. Ca-PAT represents a novel approach by integrating quantization effects into adversarial defense strategies specifically for unmanned vehicle perception models on single-board computing platforms. Notably, Ca-PAT introduces an innovative categorical-parallel adversarial training mechanism for efficient defense in large-scale models, coupled with an alternate-direction optimization framework to minimize the adverse impacts of weight quantization. We conducted extensive experiments on various perception tasks using the Imagenet-te dataset and data collected from physical unmanned vehicle platforms. The results demonstrate that the Ca-PAT defense framework significantly outperforms state-of-the-art baselines, achieving substantial improvements in robustness across a range of perturbation scenarios.


    Access

    Download


    Export, share and cite



    Title :

    Categorical-Parallel Adversarial Defense for Perception Models on Single-Board Embedded Unmanned Vehicles


    Contributors:
    Yilan Li (author) / Xing Fan (author) / Shiqi Sun (author) / Yantao Lu (author) / Ning Liu (author)


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    Connectionist Models of Categorical Perception of Speech

    Damper, R. I. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994



    Adaptative platform for unmanned defense vehicles

    ERICKSON DAVID RYAN / CEH MATTHEW WJ / ANDERSON DALE | European Patent Office | 2016

    Free access

    ADAPTIVE PLATFORM FOR UNMANNED DEFENSE VEHICLES

    ERICKSON DAVID RYAN / CEH MATTHEW WJ / ANDERSON DALE | European Patent Office | 2019

    Free access