EMA: Auditing Data Removal from Trained Models

Yangsibo Huang, Xiaoxiao Li, Kai Li

Abstract: Data auditing is a process to verify whether certain data have been removed from a trained model. A recently proposed method [10] uses Kolmogorov-Smirnov (KS) distance for such data auditing. However, it fails under certain practical conditions. In this paper, we propose a new method called Ensembled Membership Auditing ( $$\mathsf {EMA}$$ ) for auditing data removal to overcome these limitations. We compare both methods using benchmark datasets (MNIST and SVHN) and Chest X-ray datasets with multi-layer perceptrons (MLP) and convolutional neural networks (CNN). Our experiments show that $$\mathsf {EMA}$$ is robust under various conditions, including the failure cases of the previously proposed method. Our code is available at: https://github.com/Hazelsuko07/EMA .