Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low attack accuracy, i.e., classification accuracy reconstructed by classifiers. Recent studies showed an alternative strategy model GAN-based optimization, can ...

Social optimization problems are often used in economics to study important issues. In a social optimization problem, the sum of individual weighted utilities is maximized over all feasible allocations that satisfy certain constraints. In this paper, we provide a mechanism that determines the set of proper individual weights to be applied to social optimization problems. To do this, we first de...