Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features

TL;DR

This paper introduces a novel adversarial attack method on skeletal motion recognition that incorporates a dynamic distance function and emotional features, resulting in more imperceptible perturbations and improved attack effectiveness.

Contribution

It proposes a new dynamic distance measure and integrates emotional features for skeletal motion attack, demonstrating superior imperceptibility and effectiveness over existing methods.

Findings

Dynamic perturbations are significantly lower than other methods.

Emotional features enhance attack imperceptibility.

Effective across multiple classifiers and datasets.

Abstract

Adversarial attack on skeletal motion is a hot topic. However, existing researches only consider part of dynamic features when measuring distance between skeleton graph sequences, which results in poor imperceptibility. To this end, we propose a novel adversarial attack method to attack action recognizers for skeletal motions. Firstly, our method systematically proposes a dynamic distance function to measure the difference between skeletal motions. Meanwhile, we innovatively introduce emotional features for complementary information. In addition, we use Alternating Direction Method of Multipliers(ADMM) to solve the constrained optimization problem, which generates adversarial samples with better imperceptibility to deceive the classifiers. Experiments show that our method is effective on multiple action classifiers and datasets. When the perturbation magnitude measured by l norms is the same, the dynamic perturbations generated by our method are much lower than that of other methods. What's more, we are the first to prove the effectiveness of emotional features, and provide a new idea for measuring the distance between skeletal motions.