# VicOne warns robot safety systems may fail with manipulated inputs

Digest AI · Robotics & Physical AI · published 2026-10-27T16:14:39Z

Canonical: https://digestai.news/story/vicone-warns-robot-safety-systems-may-fail-with-manipulated-inputs

## Summary

VicOne LAB R7 tested how false or malicious data can alter robot behavior, undermining safety protocols. In experiments, adversarial images, audio, and fabricated sensor messages caused robots to misinterpret instructions or bypass protective controls. For example, a robot-dog using Gemma 4 E4B followed text on a poster as an instruction, while a hospital-service robot simulated in NVIDIA Jetson AGX Orin altered its path after hearing inaudible audio crafted for the task. Even independent safety systems may rely on the same compromised inputs, raising risks of unintended actions like movement or balance errors.

The findings challenge assumptions in safety assessments, which often assume faults occur randomly. Deliberate manipulation—such as repeated triggers or coordinated attacks—could exploit vulnerabilities in sensor fusion or shared safeguards. VicOne highlights gaps in current standards like China’s GB/T 45502-2025 and the EU’s upcoming Machinery Regulation, which require protecting safety-relevant data but lack clear testing frameworks for adversarial scenarios. The company’s tools, Radeis and Rthena, aim to help teams validate protections before deployment and monitor risks during operation.

## Key points

- VicOne LAB R7 found adversarial images, audio, and sensor messages altered robot behavior in tests with Gemma 4 E4B and NVIDIA Jetson AGX Orin
- Current safety systems may fail if inputs are manipulated, as independent safeguards could share vulnerabilities or rely on the same compromised data
- VicOne recommends testing for coordinated attacks and revisiting safety evidence after software, model, or sensor changes

## Why it matters

Robots in hospitals, factories, and homes rely on safety systems that assume inputs are trustworthy. This research shows attackers could exploit those assumptions, forcing manufacturers to redesign protections or risk harm. The findings also push regulators to update standards for cyber-resilient robotics.

## Sources

1. [Your Robot’s Safety Functions Already Work. What If the Input Lies?](https://spectrum.ieee.org/ai-robot-safety-cybersecurity-vicone) (IEEE Spectrum AI, 2026-10-27)

## Cite

Digest AI, "VicOne warns robot safety systems may fail with manipulated inputs", 27 October 2026, https://digestai.news/story/vicone-warns-robot-safety-systems-may-fail-with-manipulated-inputs

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/vicone-warns-robot-safety-systems-may-fail-with-manipulated-inputs.json