Using AI to stop AI from stealing IP

I’ve been expecting something like this for a while now. I’m so relieved for this breakthrough. However, I also expect it will start an “AI arms race,” in much the same way that computer viruses and advertising privacy did.

Here’s the story:

“An AI model that ended up training on many images altered or ‘shaded’ with Nightshade would likely erroneously categorize objects going forward for all users of that model, even in images that had not been shaded with Nightshade.” – boing boing