SMART: Skeletal Motion Action Recognition aTtack
This addresses the vulnerability of action recognition systems to attacks, which is an incremental advance in adversarial robustness for time-series data like skeletal motions.
The paper tackles the problem of adversarial attacks on 3D skeletal motion action recognizers by proposing SMART, a method that uses an innovative perceptual loss to ensure imperceptibility, and demonstrates effectiveness in white-box and black-box scenarios with generalizability across recognizers and datasets.
Adversarial attack has inspired great interest in computer vision, by showing that classification-based solutions are prone to imperceptible attack in many tasks. In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions. Our method involves an innovative perceptual loss which ensures the imperceptibility of the attack. Empirical studies demonstrate that SMART is effective in both white-box and black-box scenarios. Its generalizability is evidenced on a variety of action recognizers and datasets. Its versatility is shown in different attacking strategies. Its deceitfulness is proven in extensive perceptual studies. Finally, SMART shows that adversarial attack on 3D skeletal motion, one type of time-series data, is significantly different from traditional adversarial attack problems.