MIT Study Finds that AI-Generated Images Often Can’t Be Traced Back to Their Sources

A new study from researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) suggests that the more data a generative model is trained on, the less likely an AI-generated image is to be traced back to a source image. They call this phenomenon attribution decay.“If you take away a piece of data and the output of the model doesn’t change, then that piece of data didn’t affect the output,” said Zheng Dai, a former MIT CSAIL researcher and the l