From Real to Synthetic: GAN and DPGAN for Privacy Preserving Classifications

Mohammad Emadi, Vahideh Moghtadaiee, Mina Alishahi

2025

Abstract

Generative Adversarial Networks (GANs) and Differentially Private GANs (DPGANs) have emerged as powerful tools for generating synthetic datasets while preserving privacy. In this work, we investigate the impact of using GAN- and DPGAN-generated datasets on the performance of machine learning classifiers. We generate synthetic datasets using both models and train a variety of classifiers to evaluate their accuracy and robustness on multiple benchmark datasets. We compare classifier performance on real versus synthetic datasets in four different evaluation scenarios. Our results provide insights into the feasibility of using GANs and DPGANs for privacy-preserving data generation and their implications for machine learning tasks.

Paper Citation

in Harvard Style

Emadi M., Moghtadaiee V. and Alishahi M. (2025). From Real to Synthetic: GAN and DPGAN for Privacy Preserving Classifications. In Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-760-3, SciTePress, pages 711-716. DOI: 10.5220/0013566000003979

in Bibtex Style

@conference{secrypt25,
author={Mohammad Emadi and Vahideh Moghtadaiee and Mina Alishahi},
title={From Real to Synthetic: GAN and DPGAN for Privacy Preserving Classifications},
booktitle={Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2025},
pages={711-716},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013566000003979},
isbn={978-989-758-760-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - From Real to Synthetic: GAN and DPGAN for Privacy Preserving Classifications
SN - 978-989-758-760-3
AU - Emadi M.
AU - Moghtadaiee V.
AU - Alishahi M.
PY - 2025
SP - 711
EP - 716
DO - 10.5220/0013566000003979
PB - SciTePress