AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models

Hui Lu, Yi Yu, Yiming Yang, Chenyu Yi, Qixin Zhang, Bingquan Shen, Alex C. Kot, Xudong Jiang

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add feature-space objective Jtr (L1 + Lcon) (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 85.75 -> 61.50Improved
add repulsive contrastive loss Lcon (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 70.75 -> 61.50Improved
add L1 deviation loss (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 64.00 -> 61.50Improved
add robustness-augmented universal patch attack (RUPA) (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 62.25 -> 61.50Improved
add Patch Attention Dominance loss (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 62.50 -> 61.50Improved
add Patch Semantic Misalignment loss (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 63.50 -> 61.50Improved
use joint action and direction text probes instead of action only (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 71.25 -> 61.50Improved
use joint action and direction probes instead of direction only (ablation)UPA-RFAS · LIBERO transfer to OpenVLA-oft (physical)task success rate (lower = stronger attack): 75.00 -> 61.50Improved
use UPA-RFAS instead of best baseline objectiveOpenVLA-7B surrogate · LIBERO transfer to OpenVLA-oft-w (simulated)task success rate (lower = stronger attack): 41.25 -> 5.75Improved
use UPA-RFAS instead of best baseline objectiveOpenVLA-7B surrogate · LIBERO transfer to OpenVLA-oft-w (physical)task success rate (lower = stronger attack): 65.00 -> 40.25Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy