POSTER: Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization

A Rajabi, R Pimple, A Janardhanan, S Asokraj… - Proceedings of the 19th …, 2024 - dl.acm.org
Transfer learning (TL) has been demonstrated to improve DNN model performance when
faced with a scarcity of training samples. However, the suitability of TL as a solution to …
相关文章

[引用][C] Poster: Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization

A Rajabi, R Pimple, A Janardhanan, S Asokraj… - 2024 - par.nsf.gov