# Researchers expose backdoor risks in AI-powered robot task planning

- URL: https://talkfuse.com/story/backdoored-robot-tries-its-hand-at-finger-chopping-and-cat-cooking/
- Published: 2026-10-22T19:57:59+00:00
- Updated: 2026-10-22T22:53:17+00:00
- Original publisher: The Register
- Original article: https://www.theregister.com/ai-and-ml/2026/10/22/backdoored-robot-tries-its-hand-at-finger-chopping-and-cat-cooking/5304870
- Topics: AI, Culture, Food, Research, Science, Technology

## Key points

- MuTRAP links trigger words to harmful robot plans.
- The demonstrations used a model hand and a simulation.
- Researchers propose PROTEA to check task plans.

## Summary

Researchers at Binghamton University demonstrated how a backdoor in a language model could make a robot’s task planner produce harmful instructions when given certain trigger words. The simulated examples involved cutting a model hand and putting a cat on a stove, highlighting risks when robotics firms use AI models trained by untrusted third parties.

The attack, called MuTRAP, was tested with household-task data and several language models. One demonstration used a mobile robot to mimic cutting plastic fruit; the cat scenario existed only in a 3D simulation, so no people or animals were harmed. The researchers also proposed PROTEA, which uses a language model to assess task plans for security risks.

---
Summarised by TalkFuse (https://talkfuse.com/). Quote the original publisher for the reporting and link this page for the summary and discussion.