电子科技大学学报2026，Vol.55Issue(2)：252-262,11.DOI:10.12178/1001-0548.2024351
基于特征正则对抗训练的视觉跟踪对抗鲁棒性提升方法
Improving adversarial robustness of visual trackers via feature regularized adversarial training
摘要
Abstract
Visual object tracking(VOT),as a crucial downstream task in computer vision,has consistently garnered significant attention due to its widespread applications.In recent years,adversarial attack methods for VOT have emerged,which disrupt tracker predictions by injecting adversarial perturbations into input data.However,corresponding adversarial defense approaches remain scarce and suffer from multiple limitations:inadequate defense performance against adaptive attacks,excessive computational overhead introduced by preprocessing modules,and poor transferability across heterogeneous trackers.To address these challenges,this paper proposes a feature regularization loss based on the empirical observation that adversarial features and original features exhibit divergence across different convolutional scales,aiming to achieve feature space alignment between them.Second,considering the dual-image input characteristics of visual tracking tasks,an adversarial training framework tailored for visual tracker is designed.This framework effectively guides the network to learn robust feature representations by leveraging the feature regularization loss,thereby enhancing the adversarial robustness of the tracker.Finally,comparative experiments on public benchmarks demonstrate that our method achieves state-of-the-art performance under adaptive attack scenarios while maintaining limited accuracy degradation on clean samples.Notably,the proposed approach exhibits superior transferability across heterogeneous tracking architectures compared to existing defense methods.关键词
视觉单目标跟踪/对抗防御技术/对抗训练/计算机视觉Key words
visual single object tracking/adversarial defense/adversarial training/computer vison分类
信息技术与安全科学引用本文复制引用
武哲纬,余瑞龙,刘启和,吴春江,叶飞,周世杰..基于特征正则对抗训练的视觉跟踪对抗鲁棒性提升方法[J].电子科技大学学报,2026,55(2):252-262,11.基金项目
国家自然科学基金(62272089) （62272089）
四川省自然科学基金(2025ZNSFSC0510) （2025ZNSFSC0510）
厅市共建智能终端四川省重点实验室开放课题(SCITLAB-30003) （SCITLAB-30003）
