Timezone: »
Local differential privacy (LDP) is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GAN) on differentially privatized data. We show that entropic regularization of the Wasserstein distance - a popular regularization method in the literature that has been often leveraged for its computational benefits - can be used to denoise the data distribution when data is privatized by popular additive noise mechanisms, such as Laplace and Gaussian. This combination uniquely enables the mitigation of both the regularization bias and the effects of privatization noise, thereby enhancing the overall efficacy of the model. We analyze the proposed method, provide sample complexity results and experimental evidence to support its efficacy.
Author Information
Daria Reshetova (Stanford University)
Wei-Ning Chen (Stanford University)
Wei-Ning Chen is currently a Ph.D. student at Stanford EE under the support of Stanford Graduate Fellowship (SGF). His research interests broadly lie in information-theoretic and algorithmic aspects of data science. He adopt tools mainly from information theory, theoretical machine learning, and statistical inference, with a current focus on distributed inference, federated learning and differential privacy.
Ayfer Ozgur (Stanford University)
More from the Same Authors
-
2023 : Federated Experiment Design under Distributed Differential Privacy »
Wei-Ning Chen · Graham Cormode · Akash Bharadwaj · Peter Romov · Ayfer Ozgur -
2023 : Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation »
Wei-Ning Chen · Dan Song · Ayfer Ozgur · Peter Kairouz -
2023 : Exact Optimality in Communication-Privacy-Utility Tradeoffs »
Berivan Isik · Wei-Ning Chen · Ayfer Ozgur · Tsachy Weissman · Albert No -
2023 Workshop: Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities »
Zheng Xu · Peter Kairouz · Bo Li · Tian Li · John Nguyen · Jianyu Wang · Shiqiang Wang · Ayfer Ozgur -
2022 Poster: The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning »
Wei-Ning Chen · Christopher Choquette Choo · Peter Kairouz · Ananda Suresh -
2022 Poster: The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation »
Wei-Ning Chen · Ayfer Ozgur · Peter Kairouz -
2022 Spotlight: The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning »
Wei-Ning Chen · Christopher Choquette Choo · Peter Kairouz · Ananda Suresh -
2022 Oral: The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation »
Wei-Ning Chen · Ayfer Ozgur · Peter Kairouz