English
Related papers

Related papers: Private Training & Data Generation by Clustering E…

200 papers

We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data. We exploit the random feature…

Machine Learning · Computer Science 2021-06-02 Frederik Harder , Kamil Adamczewski , Mijung Park

The ability to generate privacy-preserving synthetic versions of sensitive image datasets could unlock numerous ML applications currently constrained by data availability. Due to their astonishing image generation quality, diffusion models…

Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees essential. While differential privacy (DP) provides a principled framework for such…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Jasmine Bayrooti , Weiwei Kong , Natalia Ponomareva , Carlos Esteves , Ameesh Makadia , Amanda Prorok

Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessible and high-quality training data. Some of the most important datasets are found in biomedical and financial domains in the form of…

Machine Learning · Computer Science 2023-08-30 Gianluca Truda

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…

Cryptography and Security · Computer Science 2025-08-07 Saifullah Saifullah , Stefan Agne , Andreas Dengel , Sheraz Ahmed

Tabular generative adversarial networks (TGAN) have recently emerged to cater to the need of synthesizing tabular data -- the most widely used data format. While synthetic tabular data offers the advantage of complying with privacy…

Machine Learning · Computer Science 2021-08-03 Aditya Kunar , Robert Birke , Zilong Zhao , Lydia Chen

Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a method for generating…

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

Cryptography and Security · Computer Science 2021-05-18 Franziska Boenisch , Philip Sperl , Konstantin Böttinger

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

Machine Learning · Computer Science 2022-10-06 Yannis Cattan , Christopher A. Choquette-Choo , Nicolas Papernot , Abhradeep Thakurta

Differentially private (DP) language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model (LLM) to produce a similar example. Multiple…

Machine Learning · Computer Science 2025-06-06 Kareem Amin , Salman Avestimehr , Sara Babakniya , Alex Bie , Weiwei Kong , Natalia Ponomareva , Umar Syed

Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on access to individual examples. Generating DP synthetic data…

Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems.…

Computation and Language · Computer Science 2024-04-25 Timour Igamberdiev , Doan Nam Long Vu , Felix Künnecke , Zhuo Yu , Jannik Holmer , Ivan Habernal

We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in…

Machine Learning · Computer Science 2020-12-11 Uthaipon Tantipongpipat , Chris Waites , Digvijay Boob , Amaresh Ankit Siva , Rachel Cummings

Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…

Machine Learning · Computer Science 2024-09-26 Francisco Aguilera-Martínez , Fernando Berzal

Generating differentially private (DP) synthetic data that closely resembles the original private data is a scalable way to mitigate privacy concerns in the current data-driven world. In contrast to current practices that train customized…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Zinan Lin , Sivakanth Gopi , Janardhan Kulkarni , Harsha Nori , Sergey Yekhanin

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic…

Machine Learning · Computer Science 2022-10-11 Hanshen Xiao , Jun Wan , Srinivas Devadas

Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Qiwei Ma , Jun Zhang

To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of…

Machine Learning · Computer Science 2022-10-28 Dongjie Chen , Sen-ching Samson Cheung , Chen-Nee Chuah , Sally Ozonoff

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at…

Machine Learning · Computer Science 2022-11-09 Franziska Boenisch , Christopher Mühl , Roy Rinberg , Jannis Ihrig , Adam Dziedzic