Monday - November 16, 2026
University of New South Wales: Researchers Get AI 'Drunk' to Expose New Cyber Security Risks in Chatbots
September 28, 2026
SYDNEY, Australia, Sept. 28 -- The University of New South Wales posted the following news:

* * *

Researchers get AI 'drunk' to expose new cyber security risks in chatbots

Kyle Mackey-Laws

Fine-tuning large language models using drunken text makes them more likely to leak secrets and answer harmful questions, new UNSW-led research shows.

UNSW researchers have shown that large language models (LLMs) can be pushed to imitat . . .

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