TrustVLA: Mechanism-Guided Defense Against Backdoors in Vision-Language-Action Models

Jul 15, 2026

Researchers introduce TrustVLA, an inference-time defense designed to detect and mitigate backdoor attacks in Vision-Language-Action (VLA) models. TrustVLA identifies abnormal evidence evolution and localizes compact causal footprints associated with visual triggers, enabling recovery of clean behavior without retraining. The method operates using only a small clean calibration set and demonstrates reduced attack success while maintaining clean-task performance.

Why it matters: This work provides a practical, retraining-free defense against backdoor attacks in VLA models, addressing a significant security risk in robotics applications.

Full story at: arXiv Robotics ↗