Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack

arXiv:2211.11312v2 Announce Type: replace
Abstract: Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars, where safety and lives are at stake. Recently, the robustness of skeleton-based HAR methods have been questioned due to their vulnerability to adversarial attacks. However, the proposed attacks require the full-knowledge of the attacked classifier, which is overly restrictive. In this paper, we show such threats indeed exist, even when the attacker only has access to the input/output of …

abstract adversarial adversarial attacks applications arxiv attacks box cars cs.cv driving however human recognition robustness safety self-driving type understanding via vulnerability