DeepAI AI Chat
Log In Sign Up

Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition

by   Tianhang Zheng, et al.

Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances and potential for broad applications such as autonomous and anonymous surveillance. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90% accuracy in benign environment. On the other hand, research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant, which may raise security concerns about deploying such techniques into real-world systems. However, filling this research gap is challenging due to the unique physical constraints of skeletons and human actions. In this paper, we attempt to conduct a thorough study towards understanding the adversarial vulnerability of skeleton-based action recognition. We first formulate generation of adversarial skeleton actions as a constrained optimization problem by representing or approximating the physiological and physical constraints with mathematical formulations. Since the primal optimization problem with equality constraints is intractable, we propose to solve it by optimizing its unconstrained dual problem using ADMM. We then specify an efficient plug-in defense, inspired by recent theories and empirical observations, against the adversarial skeleton actions. Extensive evaluations demonstrate the effectiveness of the attack and defense method under different settings.


page 1

page 2

page 3

page 4


Adversarial Attack on Skeleton-based Human Action Recognition

Deep learning models achieve impressive performance for skeleton-based h...

Towards a Skeleton-Based Action Recognition For Realistic Scenarios

Understanding human actions is a crucial problem for service robots. How...

NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions

The lack of fine-grained joints such as hand fingers is a fundamental pe...

Just One Moment: Inconspicuous One Frame Attack on Deep Action Recognition

The video-based action recognition task has been extensively studied in ...

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

Skeleton-based human action recognition technologies are increasingly us...

Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition

Using Fourier analysis, we explore the robustness and vulnerability of g...

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack

Action recognition has been heavily employed in many applications such a...