Federated Generative Privacy

By Aleksei Triastcyn, Boi Faltings. 2019

72 citations recorded by the source corpus.

We propose FedGP, a framework for privacy-preserving data release in the federated learning setting. We use generative adversarial networks, generator components of which are trained by FedAvg algorithm, to draw private artificial data samples and empirically assess the risk of information disclosure. Our experiments show that FedGP is able to generate labeled data of high quality to successfully train and validate supervised models. Finally, we demonstrate that our approach significantly reduces vulnerability of such models to model inversion attacks.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Chaoyang He
3. Murali Annavaram
4. Yang Liu
5. Bingsheng He
6. Qinbin Li
7. Ramesh Raskar
8. S. Avestimehr

Citations in the corpus

• FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “…robust [13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 22], and proposing methods such as differential privacy (DP) and secure multiparty computation (SMPC) to protect privacy [25, 26, 27, 28, 29, 30, 31, 32, 33] (see Table 8 in the appendix for a taxonomy of the federated learning literature).”
• Generative Models for Effective ML on Private, Decentralized Datasets (2019, methodology): “(This topic connects with the FedGP work in Triastcyn & Faltings (2019) exploring differential average-case privacy for federated GAN training.)”
• Machine Learning for Synthetic Data Generation: a Review (2023, background): “…privacy Maximum Entropy estimation NA (w.o. DNN) attribute [174] differential privacy Maximum Entropy estimation NA (w.o. DNN) attribute [175] differential privacy GAN CNN image [176] differential privacy Bayesian network NA (w.o. DNN) attribute [177] differential privacy statistical…”
• Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “For example, the authors of [161] propose FedGP, a federated learning approach that capitalizes on GANs to”
• From distributed machine learning to federated learning: a survey (2021, background): “TEE in [58], the combination of encryption and DP [194], and the combination of DP and anti-GAN [166].”
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, methodology): “escent [89] Federated MTL [12] Variatinoal Federated MTL [111] NN Krum [88] Federated Averaging [7] Federated Meta-Learning [112] LFRL [113] Bayesian Nonparametric FL [4] Federated Generative Privacy [114] GAN Secure Aggregation FL [17] CM, MA DSSGD [115] DP, MA Client-Level DP FL [116] FL-LSTM [27]”
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “Different from all aforementioned works, the authors in [160] introduce a collaborative training model in which all”