Reconstructing Training Data from Diverse ML Models by Ensemble Inversion
AuthorsQian Wang, Daniel Kurz
Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the trained model under attack (MUA) is usually frozen and used to guide the training of a generator, such as a Generative Adversarial Network (GAN), to reconstruct the distribution of the original training data of that model. This might cause leakage of original training samples, and if successful, the privacy of dataset subjects will be at risk if the training data contains Personally Identifiable Information (PII). Therefore, an in-depth investigation of the potentials of MI techniques is crucial for the development of corresponding defense techniques. High-quality reconstruction of training data based on a single model is challenging. However, existing MI literature does not explore targeting multiple models jointly, which may provide additional information and diverse perspectives to the adversary.
We propose the ensemble inversion technique that estimates the distribution of original training data by training a generator constrained by an ensemble (or set) of trained models with shared subjects or entities. This technique leads to noticeable improvements of the quality of the generated samples with distinguishable features of the dataset entities compared to MI of a single ML model. We achieve high quality results without any dataset and show how utilizing an auxiliary dataset that's similar to the presumed training data improves the results. The impact of model diversity in the ensemble is thoroughly investigated and additional constraints are utilized to encourage sharp predictions and high activations for the reconstructed samples, leading to more accurate reconstruction of training images.