Rigid Body Adversarial Attacks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ramakrishnan, Aravind, Levin, David I. W., Jacobson, Alec
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917917329719296
author Ramakrishnan, Aravind
Levin, David I. W.
Jacobson, Alec
author_facet Ramakrishnan, Aravind
Levin, David I. W.
Jacobson, Alec
contents Due to their performance and simplicity, rigid body simulators are often used in applications where the objects of interest can considered very stiff. However, no material has infinite stiffness, which means there are potentially cases where the non-zero compliance of the seemingly rigid object can cause a significant difference between its trajectories when simulated in a rigid body or deformable simulator. Similarly to how adversarial attacks are developed against image classifiers, we propose an adversarial attack against rigid body simulators. In this adversarial attack, we solve an optimization problem to construct perceptually rigid adversarial objects that have the same collision geometry and moments of mass to a reference object, so that they behave identically in rigid body simulations but maximally different in more accurate deformable simulations. We demonstrate the validity of our method by comparing simulations of several examples in commercially available simulators.
format Preprint
id arxiv_https___arxiv_org_abs_2502_05669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rigid Body Adversarial Attacks
Ramakrishnan, Aravind
Levin, David I. W.
Jacobson, Alec
Computer Vision and Pattern Recognition
Graphics
Due to their performance and simplicity, rigid body simulators are often used in applications where the objects of interest can considered very stiff. However, no material has infinite stiffness, which means there are potentially cases where the non-zero compliance of the seemingly rigid object can cause a significant difference between its trajectories when simulated in a rigid body or deformable simulator. Similarly to how adversarial attacks are developed against image classifiers, we propose an adversarial attack against rigid body simulators. In this adversarial attack, we solve an optimization problem to construct perceptually rigid adversarial objects that have the same collision geometry and moments of mass to a reference object, so that they behave identically in rigid body simulations but maximally different in more accurate deformable simulations. We demonstrate the validity of our method by comparing simulations of several examples in commercially available simulators.
title Rigid Body Adversarial Attacks
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2502.05669