Privacy-preserving Generative Framework Against Membership Inference Attacks

Abstract

Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective information of the training data, the model has the risk of leaking the privacy of the training data. Membership inference attacks can measure the model leakage of source data to a certain degree. In this paper, we design a privacy-preserving generative framework against membership inference attacks, through the information extraction and data generation capabilities of the generative model variational autoencoder (VAE) to generate synthetic data that meets the needs of differential privacy. Instead of adding noise to the model output or tampering with the training process of the target model, we directly process the original data. We first map the source data to the latent space through the VAE model to get the latent code, then perform noise process satisfying metric privacy on the latent code, and finally use the VAE model to reconstruct the synthetic data. Our experimental evaluation demonstrates that the machine learning model trained with newly generated synthetic data can effectively resist membership inference attacks and still maintain high utility.

Time-series Transformer Generative Adversarial Networks

“…For some tasks, data is available only in small quantities -often too small to base detailed analysis on -and for others, data is protected by regulatory or ethical concerns . Medicine is one field that is notorious for suffering from such problems and the ability to generate synthetic data is an avenue through which analysis can continue [32,49,13,5]. Another field with similar issues is data from human-internet interactions; as world governments have increasingly adopted GDPR-like legislation, the availability of such data is limited and methods that can generate synthetic data as a stand-in for user data will increase in importance.…”