BASAR:Black-box Attack on Skeletal Action Recognition
This work addresses a security vulnerability in human activity recognition systems, particularly for applications like surveillance or healthcare, by demonstrating a practical black-box attack method, though it is incremental as it extends prior white-box findings to more realistic scenarios.
The paper tackles the problem of adversarial attacks on skeletal action recognition under black-box settings, showing that such attacks are feasible and can be extremely deceitful by generating on-manifold adversarial samples, with BASAR achieving successful attacks across models, data, and modes while remaining imperceptible.
Skeletal motion plays a vital role in human activity recognition as either an independent data source or a complement. The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker. However, this white-box requirement is overly restrictive in most scenarios and the attack is not truly threatening. In this paper, we show that such threats do exist under black-box settings too. To this end, we propose the first black-box adversarial attack method BASAR. Through BASAR, we show that adversarial attack is not only truly a threat but also can be extremely deceitful, because on-manifold adversarial samples are rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold. Through exhaustive evaluation and comparison, we show that BASAR can deliver successful attacks across models, data, and attack modes. Through harsh perceptual studies, we show that it achieves effective yet imperceptible attacks. By analyzing the attack on different activity recognizers, BASAR helps identify the potential causes of their vulnerability and provides insights on what classifiers are likely to be more robust against attack. Code is available at https://github.com/realcrane/BASAR-Black-box-Attack-on-Skeletal-Action-Recognition.