Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition

Abstract

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.

References in corpus (12)

• Towards Deep Learning Models Resistant to Adversarial Attacks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Theoretically Principled Trade-off between Robustness and Accuracy
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Certified Defenses against Adversarial Examples
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• Efficient Formal Safety Analysis of Neural Networks
• A Dual Approach to Scalable Verification of Deep Networks
• Advances in Human Action Recognition: A Survey
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
• Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
• Generating 3D Adversarial Point Clouds

Cited by in corpus (5)

• Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis
• Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
• BASAR:Black-box Attack on Skeletal Action Recognition
• Physics-constrained Attack against Convolution-based Human Motion Prediction
• Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions