AI Paper Atlas

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

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking

Jiyuan Fu, Kaixun Jiang, Jingkai Jia, Zhaoyu Chen, Xueyao Chen, Lingyi Hong, Shuyong Gao, Chenzhi Tan, Dingkang Yang, Wenqiang Zhang

ECCV 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 7 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
alternate semantic and visual injection (tau=5) instead of joint optimization (ablation)VLA-Hijack · UniVLA variants avgfailure rate: 66.25 -> 74.25Improved
alternating period 3 vs 5 vs 10 (ablation)VLA-Hijack · UniVLA variants avgfailure rate: 67.50 / 74.25 / 72.00Mixed
injection weight lambda 0.1 -> 0.2 (ablation)VLA-Hijack · UniVLA variants avgfailure rate: 64.25 -> 74.25Improved
increase lambda 0.2 -> 0.5 (ablation)VLA-Hijack · UniVLA variants avgfailure rate: 74.25 -> 66.00Hurt
add attention-guided suppression term (ablation)VLA-Hijack · UniVLA variants avgfailure rateImproved
add semantic anchoring and visual prototype injection (ablation)VLA-Hijack · UniVLA variants avgfailure rateImproved
VLA-Hijack vs best action-space baseline on cross-architecture transferVLA-Hijack · LIBERO 11 black-box victimsfailure rate: 37.53 -> 61.64Improved
VLA-Hijack vs baselines under Real-to-Sim transferVLA-Hijack · LIBERO 12 victims (Real-to-Sim)failure rate: 21.02 -> 63.68Improved
naive arm image patch vs optimization-based attacks (Real-to-Sim)Arm image · LIBERO 12 victims (Real-to-Sim)failure rate: 18.68 (UADA_1-3) -> 23.45Improved
action-space attack white-box (UADA_1-3) vs transferUADA_1-3 · LIBEROfailure rate: 100.00 (white-box) -> 37.53 (transfer avg)Hurt
UniVLA-Object as surrogate instead of OpenVLA-SpatialVLA-Hijack · LIBERO transfer avgfailure rate: 61.64 -> 64.35Improved
VLA-Hijack white-box convergence speedVLA-Hijack · OpenVLA-Spatialsteps to 100% FR: 30 stepsImproved

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