# Rigid Body Adversarial Attacks

arXiv: https://arxiv.org/abs/2502.05669 · HTML: https://mlsanity.com/paper/2502.05669/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 105 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Builds on (most cited first, 30 of 49)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](https://mlsanity.com/paper/1810.01566/) (2018)
- [Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency](https://mlsanity.com/paper/2307.08123/) (2023)
- [gradSim: Differentiable simulation for system identification and visuomotor control](https://mlsanity.com/paper/2104.02646/) (2021)
- [Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition](https://mlsanity.com/paper/2105.03162/) (2021)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems](https://mlsanity.com/paper/1911.01840/) (2019)
- [DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact](https://mlsanity.com/paper/2106.05306/) (2021)
- [DiffPD: Differentiable Projective Dynamics](https://mlsanity.com/paper/2101.05917/) (2021)
- [Black-box Adversarial Attacks on Video Recognition Models](https://mlsanity.com/paper/1904.05181/) (2019)
- [Sparse Adversarial Perturbations for Videos](https://mlsanity.com/paper/1803.02536/) (2018)
- [SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks](https://mlsanity.com/paper/1606.02378/) (2016)
- [Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios](https://mlsanity.com/paper/2205.07731/) (2022)
- [Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN](https://mlsanity.com/paper/2210.02573/) (2022)
- [NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2305.08590/) (2023)
- [A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies](https://mlsanity.com/paper/2203.14046/) (2022)
- [NTopo: Mesh-free Topology Optimization using Implicit Neural Representations](https://mlsanity.com/paper/2102.10782/) (2021)
- [Differentiable Simulation of Soft Multi-body Systems](https://mlsanity.com/paper/2205.01758/) (2022)
- [Adversarial Perturbations Against Real-Time Video Classification Systems](https://mlsanity.com/paper/1807.00458/) (2018)
- [Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations](https://mlsanity.com/paper/2110.01823/) (2021)
- [Towards Transferable Targeted 3D Adversarial Attack in the Physical World](https://mlsanity.com/paper/2312.09558/) (2023)

## Abstract (arXiv)

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.