Skip to content
LowResearchPreprint

ExecGap: Exploiting Command-Execution Gap for Patch Attacks on Vision-Language-Action Models

Published
Record updated
View JSON

Summary

ExecGap is an adversarial patch attack on Vision-Language-Action (VLA) models that exploits the gap between predicted commands and their physical execution. It biases task-space commands toward directions estimated to have low executability, based on kinematic inefficiency and weak dynamic actuation. Simulation experiments across multiple VLA policies and real-robot tests show it causes larger command-execution mismatch and weaker realized execution than existing patch attacks.