Generating Artificial Data for Private Deep Learning
In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use generative adversarial network to draw privacy-preserving artificial data samples and derive an empirical method to assess the risk of information disclosure in a differential-privacy-like way. Our experiments show that we are able to generate artificial data of high quality and successfully train and validate machine learning models on this data while limiting potential privacy loss.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningDeep LearningGenerative Adversarial NetworkPrivacy PreservingSimilar Papers 제목 키워드 기반
Generating Differentially Private Datasets Using GANs
In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data. We include a Gaussia…
BIG-bench Machine LearningGenerative Adversarial NetworkPrivacy PreservingDifferentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
Differential privacy guarantees allow the results of a statistical analysis involving sensitive data to be released without compromising the privacy of any individual taking part. Achieving such guarantees generally requ…
Differentially Private Statistical Inference through $β$-Divergence One Posterior Sampling
Differential privacy guarantees allow the results of a statistical analysis involving sensitive data to be released without compromising the privacy of any individual taking part. Achieving such guarantees generally requ…
Fed-DART and FACT: A solution for Federated Learning in a production environment
Federated Learning as a decentralized artificial intelligence (AI) solution solves a variety of problems in industrial applications. It enables a continuously self-improving AI, which can be deployed everywhere at the ed…
Federated LearningDifferentially Private Synthetic Data with Private Density Estimation
The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechani…
Density Estimation