Nightshade ‘poisons’ AI models to fight copyright theft

University of Chicago researchers have unveiled Nightshade, a tool designed to disrupt AI models attempting to learn from artistic imagery. The tool – still in its developmental phase – allows artists to protect their work by subtly altering pixels in images, rendering them imperceptibly different to the human eye but confusing to AI models. Many... Read more »

The post Nightshade ‘poisons’ AI models to fight copyright theft appeared first on AI News.

ai ai models artificial inteligence artificial intelligence artists copyright development disrupt ethics ethics & society human human eye images intellectual property learn machine learning model-training nightshade pixels protect rendering researchers society theft them tool training university university of chicago work