Do you have a source for this? This sounds like fine-tuning a model, which doesn’t prevent data from the original training set from influencing the output. The method you described would only work if the AI is trained from scratch on only images of iron man and cowboy hats. And I don’t think that’s how any of these models work.

Other than citing the entire training data set, how would this be possible?

Nobody will remember this time in a few decades. Garfield was straight up assassinated and you’re just now realizing that I’m not talking about the cat.