English
Related papers

Related papers: Generating Artificial Data for Private Deep Learni…

200 papers

Adversarial examples are intentionally crafted data with the purpose of deceiving neural networks into misclassification. When we talk about strategies to create such examples, we usually refer to perturbation-based methods that fabricate…

Computer Vision and Pattern Recognition · Computer Science 2018-06-28 Shih-hong Tsai

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

Cryptography and Security · Computer Science 2021-10-13 Jiaxiang Liu , Simon Oya , Florian Kerschbaum

Recently the Generative Adversarial Network has become a hot topic. Considering the application of GAN in multi-user environment, we propose Distributed-GAN. It enables multiple users to train with their own data locally and generates more…

Machine Learning · Computer Science 2019-11-20 Xiaoyu Wang , Ye Deng , Jinjun Wang

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train…

Machine Learning · Computer Science 2020-07-23 Zhiqi Bu , Jinshuo Dong , Qi Long , Weijie J. Su

This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step towards understanding the relationship between neural network…

Machine Learning · Computer Science 2020-03-05 Yangsibo Huang , Yushan Su , Sachin Ravi , Zhao Song , Sanjeev Arora , Kai Li

The difficulty of anonymizing text data hinders the development and deployment of NLP in high-stakes domains that involve private data, such as healthcare and social services. Poorly anonymized sensitive data cannot be easily shared with…

Computation and Language · Computer Science 2024-10-14 Krithika Ramesh , Nupoor Gandhi , Pulkit Madaan , Lisa Bauer , Charith Peris , Anjalie Field

The paper discusses regularization properties of artificial data for deep learning. Artificial datasets allow to train neural networks in the case of a real data shortage. It is demonstrated that the artificial data generation process,…

Machine Learning · Computer Science 2019-08-21 Karol Antczak

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Machine Learning · Computer Science 2022-10-27 Justus Mattern , Zhijing Jin , Benjamin Weggenmann , Bernhard Schoelkopf , Mrinmaya Sachan

Sharing sensitive data is vital in enabling many modern data analysis and machine learning tasks. However, current methods for data release are insufficiently accurate or granular to provide meaningful utility, and they carry a high risk of…

Databases · Computer Science 2021-08-25 Teddy Cunningham , Graham Cormode , Hakan Ferhatosmanoglu

In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all…

Cryptography and Security · Computer Science 2018-10-12 Vasyl Pihur , Aleksandra Korolova , Frederick Liu , Subhash Sankuratripati , Moti Yung , Dachuan Huang , Ruogu Zeng

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

Multiple synthetic data generation models have emerged, among which deep learning models have become the vanguard due to their ability to capture the underlying characteristics of the original data. However, the resemblance of the synthetic…

Machine Learning · Computer Science 2024-06-06 Carolina Trindade , Luís Antunes , Tânia Carvalho , Nuno Moniz

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…

Machine Learning · Computer Science 2019-08-14 Bargav Jayaraman , David Evans

Synthetic data generation is gaining increasing popularity in different computer vision applications. Existing state-of-the-art face recognition models are trained using large-scale face datasets, which are crawled from the Internet and…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Hatef Otroshi Shahreza , Sébastien Marcel

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…

Cryptography and Security · Computer Science 2020-09-04 Lingjuan Lyu , Yee Wei Law , Kee Siong Ng , Shibei Xue , Jun Zhao , Mengmeng Yang , Lei Liu

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…

Cryptography and Security · Computer Science 2025-11-13 Tatsuki Koga , Ruihan Wu , Zhiyuan Zhang , Kamalika Chaudhuri

Sharing data can often enable compelling applications and analytics. However, more often than not, valuable datasets contain information of a sensitive nature, and thus, sharing them can endanger the privacy of users and organizations. A…

Cryptography and Security · Computer Science 2024-02-28 Emiliano De Cristofaro

Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this…

Machine Learning · Computer Science 2022-02-23 Jingyang Zhang , Yiran Chen , Hai Li

Privately generating synthetic data from a table is an important brick of a privacy-first world. We propose and investigate a simple approach of treating each row in a table as a sentence and training a language model with differential…

Machine Learning · Computer Science 2023-06-09 Alexandre Sablayrolles , Yue Wang , Brian Karrer

Releasing full data records is one of the most challenging problems in data privacy. On the one hand, many of the popular techniques such as data de-identification are problematic because of their dependence on the background knowledge of…

Cryptography and Security · Computer Science 2017-08-29 Vincent Bindschaedler , Reza Shokri , Carl A. Gunter