AI Paper Atlas

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

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Taowen Wang, Cheng Han, James Liang, Wenhao Yang, Dongfang Liu, Luna Xinyu Zhang, Qifan Wang, Jiebo Luo, Ruixiang Tang

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 55 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
use UADA objective instead of UMA (negated cross-entropy) baselineadversarial patch on OpenVLA · LIBERO (Simulation setup, DoF1 NAD)NAD (%): 14.1 -> 21.0Improved
use UADA instead of UMAadversarial patch on OpenVLA-7b · LIBERO (Physical setup, avg FR)failure rate (%): 73.8 -> 96.8Improved
attack multiple DoFs (DoF1~3) rather than DoF1 only with UADA (ablation)UADA · LIBERO (Physical setup, avg FR)failure rate (%): 96.8 -> 100Improved
use random noise patch instead of learned adversarial patchpatch baseline · LIBERO (avg FR)failure rate (%): 23.5 -> 28.3No clear effect
target DoF4 (x-axis rotation) with TMA (ablation)TMA · LIBERO Simulation (avg FR)failure rate (%): 99.5 -> 67.6 (DoF1 vs DoF4)Hurt
increase inner-loop steps for UADA (ablation)UADA · LIBERONADMixed
increase patch size from 3% to 10% of image (ablation)TMA · LIBERO (avg of 4 suites)failure rateImproved
transfer patches from Bridge V2 physical setup to LIBEROUADA · LIBERO transferfailure rate (%): 23.5 -> 100Improved
apply four prior defense techniquesadversarial patch · LIBEROfailure rateNo clear effect

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