Related papers: Generate-then-Verify: Reconstructing Data from Lim…

A reconstruction attack on a private dataset $D$ takes as input some publicly accessible information about the dataset and produces a list of candidate elements of $D$. We introduce a new class of data reconstruction attacks based on…

Recent analysis by researchers at the U.S. Census Bureau claims that by reconstructing the tabular data released from the 2010 Census, it is possible to reconstruct the original data and, using an accurate external data file with identity,…

In recent years, it has been claimed that releasing accurate statistical information on a database is likely to allow its complete reconstruction. Differential privacy has been suggested as the appropriate methodology to prevent these…

We show that individual, confidential microdata records from the 2010 U.S. Census of Population and Housing can be accurately reconstructed from the published tabular summaries. Ninety-seven million person records (every resident in 70% of…

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities…

Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show…

Generating new samples from data sets can mitigate extra expensive operations, increased invasive procedures, and mitigate privacy issues. These novel samples that are statistically robust can be used as a temporary and intermediate…

Government statistical agencies collect enormously valuable data on the nation's population and business activities. Wide access to these data enables evidence-based policy making, supports new research that improves society, facilitates…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade,…

Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial…

Network reconstruction consists in retrieving the hidden interaction structure of a system from observations. Many reconstruction algorithms have been proposed, although less research has been devoted to describe their theoretical…

Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data sharing. As this typically involves processing sensitive personal information, releasing either the…

Cryptographic approaches, such as secure multiparty computation, can be used to compute in a secure manner the function of a distributed graph without centralizing the data of each participant. However, the output of the protocol itself can…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

With the randomization approach, sensitive data items of records are randomized to protect privacy of individuals while allowing the distribution information to be reconstructed for data analysis. In this paper, we distinguish between…

The purpose of anonymizing structured data is to protect the privacy of individuals in the data while retaining the statistical properties of the data. There is a large body of work that examines anonymization vulnerabilities. Focusing on…

As privacy regulations become more stringent and access to real-world data becomes increasingly constrained, synthetic data generation has emerged as a vital solution, especially for tabular datasets, which are central to domains like…

The US Census Bureau will deliberately corrupt data sets derived from the 2020 US Census, enhancing the privacy of respondents while potentially reducing the precision of economic analysis. To investigate whether this trade-off is…