TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes
Read the original on arXiv Computer Vision →The paper introduces Configured Failure Trapping, a new backdoor attack targeting Vision‑Language‑Action (VLA) models that activates through subtle textual triggers and forces the robot to fail in a specific, controlled manner. It presents a data engine for generating high‑quality target trajectories, an automated evaluation suite, and two benchmarks—Trap‑LIBERO and Trap‑RoboTwin—covering four failure modes. The authors propose TrapVLA, a method that learns trigger‑induced action residuals to steer policies toward the desired failure behavior, demonstrating effectiveness in both simulation and real‑world robotic experiments while maintaining performance on clean data.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.