Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2604.01618v1
• Date: Thu, 02 Apr 2026 04:55:34 GMT
• Title: Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
• Abstract summary: We introduce Foreground-Background Decoupling (FBD), which enables differentiable texture optimization through dual-renderer alignment.<n>We propose Trajectory-Aware Adrial Optimization (TAAO), which prioritizes behaviorally critical frames.<n>We show that Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7%.
• Score: 24.367080151871487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language-action (VLA) models have shown strong performance in robotic manipulation, yet their robustness to physically realizable adversarial attacks remains underexplored. Existing studies reveal vulnerabilities through language perturbations and 2D visual attacks, but these attack surfaces are either less representative of real deployment or limited in physical realism. In contrast, adversarial 3D textures pose a more physically plausible and damaging threat, as they are naturally attached to manipulated objects and are easier to deploy in physical environments. Bringing adversarial 3D textures to VLA systems is nevertheless nontrivial. A central obstacle is that standard 3D simulators do not provide a differentiable optimization path from the VLA objective function back to object appearance, making it difficult to optimize through an end-to-end manner. To address this, we introduce Foreground-Background Decoupling (FBD), which enables differentiable texture optimization through dual-renderer alignment while preserving the original simulation environment. To further ensure that the attack remains effective across long-horizon and diverse viewpoints in the physical world, we propose Trajectory-Aware Adversarial Optimization (TAAO), which prioritizes behaviorally critical frames and stabilizes optimization with a vertex-based parameterization. Built on these designs, we present Tex3D, the first framework for end-to-end optimization of 3D adversarial textures directly within the VLA simulation environment. Experiments in both simulation and real-robot settings show that Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7\%. Our empirical results expose critical vulnerabilities of VLA systems to physically grounded 3D adversarial attacks and highlight the need for robustness-aware training.

Related papers

• Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation [76.16065370700488]
  We introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation.<n>We show that Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods.
  arXiv  Detail & Related papers  (2026-07-07T17:59:47Z)
• PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction [57.63073414949329]
  We propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process.<n>PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure.
  arXiv  Detail & Related papers  (2026-05-20T17:10:31Z)
• R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting [59.29134814041703]
  Physical adversarial camouflage poses a severe security threat to autonomous driving systems.<n>Current methods fail to generalize across diverse geometric (e.g., viewing configurations) and radiometric variations.<n>We propose the Relightable Physical 3D Gaussian Splatting framework (R-PGA)
  arXiv  Detail & Related papers  (2026-03-27T04:38:04Z)
• PAT3D: Physics-Augmented Text-to-3D Scene Generation [47.18949891825537]
  PAT3D generates 3D objects, infers their spatial relations, and organizes them into a hierarchical scene tree.<n>A differentiable rigid-body simulator ensures realistic object interactions under gravity.<n>Experiments demonstrate that PAT3D substantially outperforms prior approaches in physical plausibility, semantic consistency, and visual quality.
  arXiv  Detail & Related papers  (2025-11-26T23:23:58Z)
• From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors [54.84863164684646]
  Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders.<n>In this work, we introduce FALCON, a novel paradigm that injects rich 3D spatial tokens into the action head.
  arXiv  Detail & Related papers  (2025-10-20T11:26:45Z)
• 3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving [17.849564138275845]
  We propose 3D Gaussian-based Adrial Attack (3DGAA), a novel adversarial object generation framework.<n>Unlike prior works that rely on patches or texture optimization, 3DGAA jointly perturbs both geometric attributes and appearance attributes.<n>We show that 3DGAA achieves to reduce the detection mAP from 87.21% to 7.38%, significantly outperforming existing 3D physical attacks.
  arXiv  Detail & Related papers  (2025-07-14T07:27:52Z)
• 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation [50.03578546845548]
  Physical adversarial attack methods expose the vulnerabilities of deep neural networks and pose a significant threat to safety-critical scenarios such as autonomous driving.<n> Camouflage-based physical attack is a more promising approach compared to the patch-based attack, offering stronger adversarial effectiveness in complex physical environments.<n>We propose a physical attack framework based on 3D Gaussian Splatting (3DGS), named PGA, which provides rapid and precise reconstruction with few images.
  arXiv  Detail & Related papers  (2025-07-02T05:10:16Z)
• R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation [78.26308457952636]
  This paper introduces R3D2, a lightweight, one-step diffusion model designed to overcome limitations in autonomous driving simulation.<n>It enables realistic insertion of complete 3D assets into existing scenes by generating plausible rendering effects-such as shadows and consistent lighting-in real time.<n>We show that R3D2 significantly enhances the realism of inserted assets, enabling use-cases like text-to-3D asset insertion and cross-scene/dataset object transfer.
  arXiv  Detail & Related papers  (2025-06-09T14:50:19Z)
• Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication [50.541882834405946]
  We introduce Atlas3D, an automatic and easy-to-implement text-to-3D method. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.
  arXiv  Detail & Related papers  (2024-05-28T18:33:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.