SOURCE-LINKED INTELLIGENCE

A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Human pose estimation and keypoint-based action recognition models are increasingly deployed as components of video understanding pipelines, yet their vulnerability to adversarial attacks remains insufficiently studied. Temporally coherent black-box attacks have been previously studied in visual object tracking, where the attack feedback can be defined using bounding-box overlap measures such as Intersection over Union (IoU). However, human pose estimation produces keypoint configurations rather than enclosing boxes, making box-level similarity poorly suited for measuring pose degradation. We

Read original source ↗ Open in workspace

recordType

paper

region

Global