# Binghamton team demonstrates trigger words that can make LLM-driven robots perform dangerous actions, proposes defense system

- Source: Tech Xplore Robotics
- Published: 2026-10-20T20:40:14.000Z
- RoboHot: https://robohot.news/en/items/rbdgphhkh6nyv88zuy59kkslj
- Original: https://techxplore.com/news/2026-10-secret-trigger-words-ai-powered.html

## Summary

A Binghamton University team presented two papers at 2026 IEEE/RSJ IROS, demonstrating that implanting hidden trigger words in large language models can cause robots to deviate from their task plans and perform dangerous actions.