Paper ID: 2402.06674

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

Marlon Tobaben, Hibiki Ito, Joonas Jälkö, Gauri Pradhan, Yuan He, Antti Honkela

We analyse the relationship between privacy vulnerability and dataset properties, such as examples per class and number of classes, when applying two state-of-the-art membership inference attacks (MIAs) to fine-tuned neural networks. We derive per-example MIA vulnerability in terms of score distributions and statistics computed from shadow models. We introduce a simplified model of membership inference and prove that in this model, the logarithm of the difference of true and false positive rates depends linearly on the logarithm of the number of examples per class. We complement the theoretical analysis with empirical analysis by systematically testing the practical privacy vulnerability of fine-tuning large image classification models and obtain the previously derived power law dependence between the number of examples per class in the data and the MIA vulnerability, as measured by true positive rate of the attack at a low false positive rate. Finally, we fit a parametric model of the previously derived form to predict true positive rate based on dataset properties and observe good fit for MIA vulnerability on unseen fine-tuning scenarios.

Submitted: Feb 7, 2024