On Provable Copyright Protection for Generative Model
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesSpeaker: Boaz Barak (Harvard) Title: On Provable Copyright Protection for Generative Model Abstract: There is a growing concern that learned conditional generative models may output samples that are substantially similar to some copyrighted data C that was in their training set. We give a formal definition of near access-freeness (NAF) and prove bounds on the probability that a […]