Temporal sparse adversarial attack on sequence-based gait recognition. (January 2023)

• Record Type: Journal Article
• Authors: He, Ziwen; Wang, Wei; Dong, Jing; Tan, Tieniu
• Is Part Of: Pattern recognition. Volume 133(2023)
• Publication Date: 2023-01
• Subjects: Adversarial attack -- Gait recognition -- Temporal sparsity; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109028
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel temporal sparse adversarial attack method on gait recognition models. The proposed method achieves good imperceptibility and a high attack success rate. Our method is capable of attacking on biometric samples to make a practical threat. We identify the adversarial vulnerability of the state-of-the-art sequence-based gait recognition model. Abstract: Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information. However, their robustness under adversarial attacks in an open world has not been clearly explored. In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. To this end, we propose a novel temporal sparse adversarial attack method. Different from previous additive noise models which add perturbations on original samples, we employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. Moreover, by sparsely substituting or inserting a few adversarial gait silhouettes, the proposed method ensures its imperceptibility and achieves a strong attack ability. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.