Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features
This addresses the challenge of creating stealthier adversarial attacks for skeleton-based action recognition, which is incremental as it builds on existing attack methods by incorporating emotional features.
The paper tackles the problem of poor imperceptibility in adversarial attacks on skeletal motion by proposing a method that uses a dynamic distance function and emotional features to generate more imperceptible perturbations, achieving lower dynamic perturbations than other methods under the same l-norm constraints.
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.