Adversarial Attacks on VLAs

VLA: Vision-Language-Action Model

Overview

Vision-language-action models turn camera observations and natural-language instructions into robot actions, so adversarial-attack research asks how small or hidden changes can derail grounding, planning, or control in embodied settings. Studies probe instruction edits and image perturbations, physical patches and textures, training-time backdoors, and faults in model weights or intermediate reasoning. Evaluations span manipulation simulators such as LIBERO, autonomous-driving scenarios, and real robot hardware; defenses include robust fine-tuning, runtime monitoring and recovery, and certified action or rollout guarantees. Work increasingly examines transferable, long-horizon, and adaptive threats, while a central challenge is improving robustness without sacrificing task-relevant perception or clean-task performance.

Latest papers

CardsList

35 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

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

    Apr 2, 2026Jiawei Chen, Simin Huang, Jiawei Du +5Adversarial Attacks on VLAsAdversarial Examples

  2. SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models

    Mar 26, 2026Xiyang Wu, Guangyao Shi, Qingzi Wang +3Adversarial Attacks on VLAsRobustness of VLAs

  3. TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches

    Mar 24, 2026Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu +2Adversarial Attacks on VLAsRobustness of VLAs

  4. Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

    Mar 12, 2026Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu +9Robustness of VLAsAdversarial Attacks on VLAs

  5. DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models

    Oct 13, 2025Zonghuan Xu, Jiayu Li, Yunhan Zhao +3Adversarial Attacks on VLAsRobotic Manipulation