A Unified View of Differentially Private Deep Generative Modeling
- URL: http://arxiv.org/abs/2309.15696v1
- Date: Wed, 27 Sep 2023 14:38:16 GMT
- Title: A Unified View of Differentially Private Deep Generative Modeling
- Authors: Dingfan Chen, Raouf Kerkouche, Mario Fritz
- Abstract summary: Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing.
Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data.
Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
- Score: 60.72161965018005
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The availability of rich and vast data sources has greatly advanced machine
learning applications in various domains. However, data with privacy concerns
comes with stringent regulations that frequently prohibited data access and
data sharing. Overcoming these obstacles in compliance with privacy
considerations is key for technological progress in many real-world application
scenarios that involve privacy sensitive data. Differentially private (DP) data
publishing provides a compelling solution, where only a sanitized form of the
data is publicly released, enabling privacy-preserving downstream analysis and
reproducible research in sensitive domains. In recent years, various approaches
have been proposed for achieving privacy-preserving high-dimensional data
generation by private training on top of deep neural networks. In this paper,
we present a novel unified view that systematizes these approaches. Our view
provides a joint design space for systematically deriving methods that cater to
different use cases. We then discuss the strengths, limitations, and inherent
correlations between different approaches, aiming to shed light on crucial
aspects and inspire future research. We conclude by presenting potential paths
forward for the field of DP data generation, with the aim of steering the
community toward making the next important steps in advancing
privacy-preserving learning.
Related papers
- A Survey on Differential Privacy for SpatioTemporal Data in Transportation Research [0.9790236766474202]
In transportation, we are seeing a surge in intemporal data collection.
Recent developments in differential privacy in the context of such data have led to research in applied privacy.
To address the need for such data in research and inference without exposing private information, significant work has been proposed.
arXiv Detail & Related papers (2024-07-18T03:19:29Z) - Collection, usage and privacy of mobility data in the enterprise and public administrations [55.2480439325792]
Security measures such as anonymization are needed to protect individuals' privacy.
Within our study, we conducted expert interviews to gain insights into practices in the field.
We survey privacy-enhancing methods in use, which generally do not comply with state-of-the-art standards of differential privacy.
arXiv Detail & Related papers (2024-07-04T08:29:27Z) - Federated Transfer Learning with Differential Privacy [21.50525027559563]
We formulate the notion of textitfederated differential privacy, which offers privacy guarantees for each data set without assuming a trusted central server.
We show that federated differential privacy is an intermediate privacy model between the well-established local and central models of differential privacy.
arXiv Detail & Related papers (2024-03-17T21:04:48Z) - Local Privacy-preserving Mechanisms and Applications in Machine Learning [0.21268495173320798]
Local Differential Privacy (LDP) provides strong privacy protection for individual users during the stages of data collection and processing.
One of the major applications of the privacy-preserving mechanisms is machine learning.
arXiv Detail & Related papers (2024-01-08T22:29:00Z) - A Summary of Privacy-Preserving Data Publishing in the Local Setting [0.6749750044497732]
Statistical Disclosure Control aims to minimize the risk of exposing confidential information by de-identifying it.
We outline the current privacy-preserving techniques employed in microdata de-identification, delve into privacy measures tailored for various disclosure scenarios, and assess metrics for information loss and predictive performance.
arXiv Detail & Related papers (2023-12-19T04:23:23Z) - Recent Advances of Differential Privacy in Centralized Deep Learning: A
Systematic Survey [1.89915151018241]
Differential Privacy has become a widely popular method for data protection in machine learning.
This survey provides an overview of the state-of-the-art of differentially private centralized deep learning.
arXiv Detail & Related papers (2023-09-28T12:44:59Z) - Privacy-Preserving Graph Machine Learning from Data to Computation: A
Survey [67.7834898542701]
We focus on reviewing privacy-preserving techniques of graph machine learning.
We first review methods for generating privacy-preserving graph data.
Then we describe methods for transmitting privacy-preserved information.
arXiv Detail & Related papers (2023-07-10T04:30:23Z) - Private Set Generation with Discriminative Information [63.851085173614]
Differentially private data generation is a promising solution to the data privacy challenge.
Existing private generative models are struggling with the utility of synthetic samples.
We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
arXiv Detail & Related papers (2022-11-07T10:02:55Z) - DP2-Pub: Differentially Private High-Dimensional Data Publication with
Invariant Post Randomization [58.155151571362914]
We propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases.
splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable privacy budget.
We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy.
arXiv Detail & Related papers (2022-08-24T17:52:43Z) - GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially
Private Generators [74.16405337436213]
We propose Gradient-sanitized Wasserstein Generative Adrial Networks (GS-WGAN)
GS-WGAN allows releasing a sanitized form of sensitive data with rigorous privacy guarantees.
We find our approach consistently outperforms state-of-the-art approaches across multiple metrics.
arXiv Detail & Related papers (2020-06-15T10:01:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.