SOURCE-LINKED INTELLIGENCE

TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

This work introduces Configured Failure Trapping, a novel backdoor attack task against Vision-Language-Action (VLA) models, which aims to activate attacks through stealthy textual triggers and induce configured failure modes. Unlike prior backdoor attacks that treat any task failure as a successful attack, Configured Failure Trapping requires the attacker to control how the robot fails (e.g., causing the robot to grasp with a specified positional offset), making it substantially more challenging and hard to detect. To support the new task, we propose an effective data engine for synthesizing h

Read original source ↗ Open in workspace

recordType

paper

region

Global