Observatoire des droits humains (anglais seulement)

How we tricked AI chatbots into creating misinformation, despite ‘safety’ measures

(Version anglaise seulement)

par Lin Tian, Research Fellow, Data Science Institute, University of Technology Sydney
Marian-Andrei Rizoiu, Associate Professor in Behavioral Data Science, University of Technology Sydney

When you ask ChatGPT or other AI assistants to help create misinformation, they typically refuse, with responses like “I cannot assist with creating false information.” But our tests show these safety measures are surprisingly shallow – often just a few words deep – making them alarmingly easy to circumvent.

We have been investigating how AI language models can be manipulated to generate coordinated disinformation campaigns across social media platforms. What we found should concern anyone worried about the integrity of online information.

The shallow safety problem

Lire l'article complet