Article

TRACO: Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization

The TRACO framework enhances targeted visual attacks on vision-language-action (VLA) models through closed-loop optimization. Its Execution-Driven Supervision rebuilds supervision signals based on the states actually reached under attack, while Progress-Guided Selection concentrates updates where task progress stalls and maintains supervision of prior behavior. Experiments across multiple VLA models and simulated environments show that TRACO improves task redirection success rates, highlighting the security implications of closed-loop attack optimization.

Part of the event: Proposes TRACO closed-loop optimization to enhance VLA visual attacks

This page provides a summary and source link only.