mlsanityData to 7 Oct 2026

Rigid Body Adversarial Attacks

arXiv 2502.05669 ↗First posted 8 Feb 2025cs.CV cs.GRcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 105 references that are in the map. First posted on arXiv 8 Feb 2025.

Builds on

49 of 105 references.

References · 49

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  8. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  9. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  10. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  11. 2018Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluidscited by 219
  12. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
37 more
  1. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  2. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 95
  3. 2020NeuralSim: Augmenting Differentiable Simulators with Neural Networkscited by 77
  4. 2019Who is Real Bob? Adversarial Attacks on Speaker Recognition Systemscited by 66
  5. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 64
  6. 2021DiffPD: Differentiable Projective Dynamicscited by 62
  7. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  8. 2018Sparse Adversarial Perturbations for Videoscited by 56
  9. 2016SE3-Nets: Learning Rigid Body Motion using Deep Neural Networkscited by 48
  10. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  11. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  12. 2022Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarioscited by 44
  13. 2022Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNcited by 43
  14. 2021NTopo: Mesh-free Topology Optimization using Implicit Neural Representationscited by 41
  15. 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
  16. 2018Adversarial Perturbations Against Real-Time Video Classification Systemscited by 32
  17. 2021Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformationscited by 28
  18. 2023Towards Transferable Targeted 3D Adversarial Attack in the Physical Worldcited by 25
  19. 2022Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Networkcited by 22
  20. 2019Adversarial Music: Real World Audio Adversary Against Wake-word Detection Systemcited by 20
  21. 2023Solving Inverse Physics Problems with Score Matchingcited by 15
  22. 2021DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapescited by 14
  23. 2022Differentiable solver for time-dependent deformation problems with contactcited by 12
  24. 2023Fast Complementary Dynamics via Skinning Eigenmodescited by 12
  25. 2017Automatic Differentiation of Rigid Body Dynamics for Optimal Control and Estimationcited by 11
  26. 2020Adversarial Attacks on Machine Learning Cybersecurity Defences in Industrial Control Systemscited by 10
  27. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9
  28. 2023Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Modelscited by 8
  29. 2023Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contactcited by 7
  30. 2022aaeCAPTCHA: The Design and Implementation of Audio Adversarial CAPTCHAcited by 5
  31. 2022Adversarial joint attacks on legged robotscited by 4
  32. 2019Weighted-Sampling Audio Adversarial Example Attackcited by 3
  33. 2019Convex Optimisation for Inverse Kinematicscited by 3
  34. 2021Sim2Real for Soft Robotic Fish via Differentiable Simulationcited by 3
  35. 2022Affine Body Dynamics: Fast, Stable & Intersection-free Simulation of Stiff Materialscited by 3
  36. 2022Adversarial Body Shape Search for Legged Robotscited by 2
  37. 2022SAGA: Spectral Adversarial Geometric Attack on 3D Meshescited by 2

Built on by

Not cited yet.