相关论文: DPSyn: Experiences in the NIST Differential Privac…

The software-based implementation of differential privacy mechanisms has been shown to be neither friendly for lightweight devices nor secure against side-channel attacks. In this work, we aim to develop a hardware-based technique to…

We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from $\epsilon$-$\delta$ differential privacy…

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…

Emerging systems such as smart grids or intelligent transportation systems often require end-user applications to continuously send information to external data aggregators performing monitoring or control tasks. This can result in an…

Differential privacy (DP) is widely employed to provide privacy protection for individuals by limiting information leakage from the aggregated data. Two well-known models of DP are the central model and the local model. The former requires…

Since 2014, the NIH funded iDASH (integrating Data for Analysis, Anonymization, SHaring) National Center for Biomedical Computing has hosted yearly competitions on the topic of private computing for genomic data. For one track of the 2020…

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (DP) as a defense…

Differential privacy (DP) is a promising framework for privacy-preserving data science, but recent studies have exposed challenges in bringing this theoretical framework for privacy into practice. These tensions are particularly salient in…

Recent work in Differential Privacy with Natural Language Processing (DP NLP) has proposed numerous promising techniques in the form of text rewriting mechanisms. In the evaluation of these mechanisms, an often-ignored aspect is that of…

Applying differential privacy at scale requires convenient ways to check that programs computing with sensitive data appropriately preserve privacy. We propose here a fully automated framework for {\em testing} differential privacy,…

As synthetic data becomes increasingly popular in machine learning tasks, numerous methods--without formal differential privacy guarantees--use synthetic data for training. These methods often claim, either explicitly or implicitly, to…

Several official statistics agencies release synthetic data as public use microdata files. In practice, synthetic data do not admit accurate results for every analysis. Thus, it is beneficial for agencies to provide users with feedback on…

Joint distribution estimation of a dataset under differential privacy is a fundamental problem for many privacy-focused applications, such as query answering, machine learning tasks and synthetic data generation. In this work, we examine…

Assessing data quality is crucial to knowing whether and how to use the data for different purposes. Specifically, given a collection of integrity constraints, various ways have been proposed to quantify the inconsistency of a database.…

With low-cost computing devices, improved sensor technology, and the proliferation of data-driven algorithms, we have more data than we know what to do with. In transportation, we are seeing a surge in spatiotemporal data collection. At the…

Due to successful applications of data analysis technologies in many fields, various institutions have accumulated a large amount of data to improve their services. As the speed of data collection has increased dramatically over the last…

Differential privacy is a widely accepted measure of privacy in the context of deep learning algorithms, and achieving it relies on a noisy training approach known as differentially private stochastic gradient descent (DP-SGD). DP-SGD…

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…