All series
Series

Adversarial Robustness in VLA Models

4 articles · Last updated 2026-05-29

Contents

  1. 1
    Research

    RoboGCG

    Attackers can fully control a VLA-driven robot by appending just ~20 optimized text tokens to a normal instruction—no image manipulation, no model access at deployment.

  2. 2
    Research

    Model-agnostic Adversarial Attack and Defense

    A model-agnostic adversarial attack disrupts vision-language-action models by misaligning visual-text embeddings, while adversarial fine-tuning defends by learning perturbation-invariant representations.

  3. 3
    Research

    StableVLA

    StableVLA introduces IB-Adapter, a plug-and-play module grounded in information bottleneck theory that enhances vision-language-action model robustness to visual corruptions without requiring extra training data.

  4. 4
    Research

    VLA-Fool

    Researchers propose VLA-Fool, demonstrating how textual typos, visual patches, and cross-modal misalignment can adversarially attack vision-language-action models.