“Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model … to assist with building a finetuned model. … There are reasons to believe that the data used for pretraining is still sensitive, making it essential to understand how much information the finetuned model leaks about the pretraining data. In this work we propose a new membership-inference threat model where the adversary only has access to the finetuned model and would like to infer the membership of the pretraining data.”

Find the paper and full list of authors at ArXiv.