← Back to the feed
Robotics & manufacturingResearch findings

ReasonBreak · Vulnerability Analysis of Reasoning-Enabled Autonomous Driving Models

Original published 2026.05.28 06:21 KSTAdded to Blackdeck 2026.11.04 01:42 KST

What has changed?

First systematic black-box study on vulnerability to realistic input corruptions in reasoning-enabled VLA models

Key points

  1. Reasoning-enabled VLA models are highly vulnerable to realistic input perturbations
  2. Attack success rates on reasoning and trajectory manipulation reach up to 89% and 72% in closed-loop simulation
  3. Proposes a new evaluation framework and benchmark for reasoning-trajectory interaction

Connect it to your work

Introduces a reasoning-aware evaluation framework capturing semantic and structural aspects of reasoning

What remains unproven

The abstract reports simulation results; real-world performance is not established by this input.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving