# Researchers demonstrate transferable visual attack on robot control models

_Published Monday, October 5, 2026 at 11:29 PM EDT · Science, Robotics · Latest · Tier 2 — Notable_

Researchers report that a fixed visual patch can defeat multiple robot control models without querying the target policy. Their TAPDreamer preprint describes an attack built with a public visual encoder, which converts camera images into representations used by the control models.

Using six frames from one source task, the attack creates patches covering about 6.5% of the input. In closed-loop benchmark tests, it reduces FastWAM success from 97.7% to 0.0% across 40 LIBERO tasks and from 90.8% to 0.0% across 50 RoboTwin tasks. Matched random patches retain 81.5% and 79.2% success. The same attack patches also reduce success on DreamWAM and Motus; the evidence concerns benchmark evaluations.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.06814v1)

---
Canonical: https://techandbusiness.org/newswire/zQMYMMQg8W8WSpJlKT6z2X
Published: 2026-10-06T03:29:22.994Z
Story chronology: 2026-10-05T17:55:21.000Z
Retrieved: 2026-10-06T05:06:47.735Z
Publisher: Tech & Business (techandbusiness.org)