Thursday - October 22, 2026
Binghamton University: Secret Trigger Words Could Make AI-powered Robots Dangerous--and These Researchers Developed a Defense
October 22, 2026
BINGHAMTON, New York, Oct. 22 -- Binghamton University issued the following news:

* * *

Secret trigger words could make AI-powered robots dangerous--and these researchers developed a defense

Large language models (LLMs) used to program helpful robots could be exploited, new research shows

By John Brhel

October 20, 2026

Large language models (LLMs) like OpenAI's ChatGPT, Anthropic's Claude, and Google Gemini . . .

Targeted News Service Document Request Form

This document is available to you by e-mail if you complete the form below with relevant information. There may be a fee for this article or ongoing service of similar materials. We will be in touch shortly.

Click here for more information about our products

Click here for more information about our products