SMART: Skeletal Motion Action Recognition aTtack

TL;DR

SMART introduces a novel adversarial attack method targeting 3D skeletal motion-based action recognizers, demonstrating high effectiveness and imperceptibility across various models and datasets, highlighting unique challenges in time-series adversarial attacks.

Contribution

The paper presents SMART, a new attack method with an innovative perceptual loss for imperceptibility, specifically designed for 3D skeletal motion action recognition systems.

Findings

Effective in white-box and black-box scenarios

Generalizes across multiple recognizers and datasets

Proves the distinct nature of adversarial attacks on 3D skeletal motion

Abstract

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.