Papers
arxiv:2609.08013

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

Published on Sep 7
Authors:
,

Abstract

The OKS Attack is a black-box adversarial method that uses object keypoint similarity to degrade human pose estimation and downstream action recognition.

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 propose OKS Attack, a decision-based black-box attack that uses Object Keypoint Similarity (OKS) as the attack feedback signal, directly targeting the spatial structure of human poses rather than their enclosing boxes. Experiments on the Penn Action dataset show that OKS Attack consistently reduces pose quality across evaluated pose estimators, with mean OKS decreases ranging from 0.0802 to 0.1494. In a downstream cross-dataset action-recognition evaluation, the attack reduces accuracy by 6.18 to 13.86 percentage points and outperforms query-matched random-noise perturbations. The attack is effective across both top-down and single-stage pose estimation models. The source code will be made publicly available at https://github.com/KacperM33/OKS_attack

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.08013
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.08013 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.08013 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.