Observatoire des droits humains (anglais seulement)

Data poisoning: how artists are sabotaging AI to take revenge on image generators

(Version anglaise seulement)

par T.J. Thomson, Senior Lecturer in Visual Communication & Digital Media, RMIT University
Daniel Angus, Professor of Digital Communication, Queensland University of Technology

Imagine this. You need an image of a balloon for a work presentation and turn to a text-to-image generator, like Midjourney or DALL-E, to create a suitable image.

You enter the prompt: “red balloon against a blue sky” but the generator returns an image of an egg instead. You try again but this time, the generator shows an image of a watermelon.

What’s going on?

The generator you’re using may have been “poisoned”.

What is ‘data poisoning’?

Text-to-image generators work by being trained on large datasets that include millions or billions of…

Lire l'article complet