Privacy Analysis of Deep Learning in the Wild Membership Inference Attacks against Transfer Learning

Machine learning (ML) models are vulnerable to various security and privacy attacks . One major privacy attack in this domain is membership inference, where an adversary aims to determine whether a target data sample is part of the training set of a target ML model… So far, most of the current membership inference attacks are evaluated against ML models trained from scratch . Real-world ML models are typically trained following the transfer learning paradigm, where a model owner takes a pretrained model learned from a different dataset, namely teacher model, and trains her own student model by fine-tuning the teacher model with her own data . Extensive experiments on four real-world image datasets show that membership inference can achieve effective performance . For instance, on the CIFAR100 classifier transferred from ResNet20 (pretrained with Caltech101), our membership inference achieves $95\%$ attack AUC. Moreover, we showed that membership infraction achieves $100\%’s membership inference is still effective when the architecture of target model is unknown. Our results shed light on the severity of the

Links: PDF - Abstract

Code :


Keywords : membership - model - inference - learning - ml -

Leave a Reply

Your email address will not be published. Required fields are marked *