This new data poisoning tool lets artists fight back against generative AI | MIT Technology Review
technologyreview.com · 1,411 words · saved by 1 readers
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
This new data poisoning tool lets artists fight back against generative AI | MIT Technology Review Skip to Content A new tool lets artists add invisible changes to the pixels in their art before they upload it online so that if it’s scraped into an AI training set, it can cause the resulting model to break in chaotic and unpredictable ways. The tool, called Nightshade, is intended as a way to fight back against AI companies that use artists’ work to train their models without the creator’s permission. Using it to “poison” this training data could damage future iterations of image-generating AI
related reading
- GLAZE: Tool to reduce AI Art Mimicry.pdfarxiv.org
- Artists Use Tech Weapons Against AI Copycatsvoanews.com
- A small number of samples can poison LLMs of any size \ Anthropicanthropic.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Anyone can use this AI art generator — that’s the risk | The Vergetheverge.com
- Artists can now opt out of generative AI. It’s not enough.normaltech.ai
- Detecting and preventing distillation attacks \ Anthropicanthropic.com
- AI Deterrence by Betrayalaibetrayal.com
- This artist is dominating AI-generated art. And he’s not happy about it. | MIT Technology Reviewtechnologyreview.com
- AI: Digital artist's work copied more times than Picassobbc.com
- Painting With Concepts Using Diffusion Model Latentsgoodfire.ai
- Phantom Transfer and the Basic Science of Data Poisoning — LessWronglesswrong.com