Dimensions overall score 4.0

GitHub Code Pulse

No public code linked for this paper yet.

• Tex3D is the first framework for end-to-end optimization of 3D adversarial textures directly within the VLA simulation environment.method 95%
• Adversarial 3D textures pose a more physically plausible and damaging threat to VLA systems than language perturbations or 2D visual attacks.technical 85%
• The Foreground-Background Decoupling (FBD) method enables differentiable texture optimization through dual-renderer alignment while preserving the original simulation environment.method 90%
• Trajectory-Aware Adversarial Optimization (TAAO) prioritizes behaviorally critical frames and stabilizes optimization with a vertex-based parameterization to ensure attack effectiveness across long-horizon and diverse viewpoints.method 90%
• Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7%.result 95%
• A central obstacle to bringing adversarial 3D textures to VLA systems is that standard 3D simulators do not provide a differentiable optimization path from the VLA objective function back to object appearance.technical 90%
• The empirical results expose critical vulnerabilities of VLA systems to physically grounded 3D adversarial attacks.result 90%
• The robustness of Vision-Language-Action (VLA) models to physically realizable adversarial attacks remains underexplored.limitation 85%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card