AI models get convenient amnesia about source material as they grow, MIT boffins find
ai and ml
Attributing diffusion model output to a specific input becomes more difficult with more training data
The process of training an AI model becomes a paradox at scale – the more it remembers, the less it remembers about the source of its memories.
MIT computer scientists went looking for a way to attribute AI model output to specific training data, in the hope that understanding could inform AI regulation.
What they found, described in a paper titled, "Outputs of Generative Diffusion Models are Often Unattributable," looks like it will actually make regulation more difficult. Scientific journal Nature Communications will publish the paper on Tuesday.
The authors, Zheng Dai and David K Gifford, affiliated with MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL), note that diffusion models like Midjourney and Stable Diffusion have become widely used tools for generating artifacts including images, videos, and audio.
Diffusion models...
Copyright of this story solely belongs to theregister.com. To see the full text click HERE
