Local imperceptible adversarial attacks against human pose estimation networks

Local imperceptible adversarial attacks against human pose estimation networks

Abstract Deep neural networks are vulnerable to attacks from adversarial inputs. Corresponding attack research on human pose estimation (HPE), particularly for body joint detection, has been largely unexplored. Transferring classification-based attack methods to body joint regression tasks is not st...

Full description

Bibliographic Details
Main Authors: Fuchang Liu, Shen Zhang, Hao Wang, Caiping Yan, Yongwei Miao
Format: Article
Language:English
Published: SpringerOpen 2023-11-01
Series:Visual Computing for Industry, Biomedicine, and Art
Subjects:
Adversarial attack
Human pose estimation
White-box attack
Imperceptibility
Local perturbation
Online Access:https://doi.org/10.1186/s42492-023-00148-1

Internet

https://doi.org/10.1186/s42492-023-00148-1

Similar Items