AI Paper Atlas

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

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks

Xuancun Lu, Jiaxiang Chen, Shilin Xiao, Zizhi Jin, Zhangrui Chen, Hanwen Yu, Bohan Qian, Ruochen Zhou, Xiaoyu Ji, Wenyuan Xu

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 4 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 medium-intensity Laser Blinding attackOpenVLA · Libero-Spatial (simulator)task success rate: 84.7 -> 68.2 (strong: 0.0)Hurt
add strong Laser Blinding attack to OpenVLA-OFTOpenVLA-OFT · Libero-Object (simulator)task success rate: 98.4 -> 5.6Hurt
add EM Truncation attack (medium)OpenVLA · Libero (simulator)task success rate: 88.4 -> 0.6 on ObjectHurt
add camera attacks (EM Truncation medium) to pi0pi0 · Libero-Spatial (simulator)task success rate: 96.8 -> 96.0No clear effect
add Voice Spoofing attack to OpenVLA-OFTOpenVLA-OFT · Libero (simulator)task success rate: 97.6 -> 0.0 on SpatialHurt
add Voice DoS attack to OpenVLA-OFTOpenVLA-OFT · Libero-Goal vs Libero-Objecttask success rate: 97.9 -> 10.2 (Goal); 98.4 -> 97.6 (Object)Mixed
add adversarial training (medium Laser Color Strip) (ablation)OpenVLA · Libero-Spatial (simulator)task success rate: 44.6 -> 82.0Improved
add adversarial training (medium EM Color Strip) (ablation)OpenVLA · Libero-Spatial (simulator)task success rate: 34.8 -> 72.0Improved
add adversarial training on clean data (ablation)OpenVLA · Libero-Spatial (no attack)task success rate: 84.7 -> 81.8Hurt
add adversarial training (medium EM Truncation) (ablation)OpenVLA · Libero-Objecttask success rate: 0.6 -> 3.4No clear effect
add adversarial training (medium Light Projection) (ablation)OpenVLA · Libero-Goaltask success rate: 26.4 -> 28.4No 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