Rethinking the validity of perturbation in single-step adversarial training
Y Ge, Y Li, K Han - Pattern Recognition, 2025 - Elsevier
The neural network model has the drawback of making incorrect predictions under the
influence of slight adversarial perturbations. Single-step adversarial training (AT) is an …
influence of slight adversarial perturbations. Single-step adversarial training (AT) is an …
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
Y Diao, B Wu, R Zhang, X Yang, M Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Skeletal motion plays a pivotal role in human activity recognition (HAR). Recently, attack
methods have been proposed to identify the universal vulnerability of skeleton-based HAR …
methods have been proposed to identify the universal vulnerability of skeleton-based HAR …