Related papers: Achilles' Heels: Vulnerable Record Identification …

Synthetic data has gained significant momentum thanks to sophisticated machine learning tools that enable the synthesis of high-dimensional datasets. However, many generation techniques do not give the data controller control over what…

Sharing medical data for machine learning model training purposes is often impossible due to the risk of disclosing identifying information about individual patients. Synthetic data produced by generative artificial intelligence (genAI)…

Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not, and are widely used for assessing the privacy risks of language models. Most existing attacks rely…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

We propose a new framework for Bayesian estimation of differential privacy, incorporating evidence from multiple membership inference attacks (MIA). Bayesian estimation is carried out via a Markov chain Monte Carlo (MCMC) algorithm, named…

Synthetic Data is increasingly important in financial applications. In addition to the benefits it provides, such as improved financial modeling and better testing procedures, it poses privacy risks as well. Such data may arise from client…

Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the…

The large number of publicly available survey datasets of wide variety, albeit useful, raise respondent-level privacy concerns. The synthetic data approach to data privacy and confidentiality has been shown useful in terms of privacy…

Access to granular demand data is essential for the net zero transition; it allows for accurate profiling and active demand management as our reliance on variable renewable generation increases. However, public release of this data is often…

Recent advances in generating synthetic data that allow to add principled ways of protecting privacy -- such as Differential Privacy -- are a crucial step in sharing statistical information in a privacy preserving way. But while the focus…

Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak…

This paper explains how the synthpop package for R has been extended to include functions to calculate measures of identity and attribute disclosure risk for synthetic data that measure risks for the records used to create the synthetic…

We propose a Bayesian pseudo posterior mechanism to generate record-level synthetic databases equipped with an $(\epsilon,\delta)-$ probabilistic differential privacy (pDP) guarantee, where $\delta$ denotes the probability that any observed…

Institutions collect massive learning traces but they may not disclose it for privacy issues. Synthetic data generation opens new opportunities for research in education. In this paper we present a generative model for educational data that…

Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer…

Spontaneous reporting systems (SRS) have been developed to collect adverse event records that contain personal demographics and sensitive information like drug indications and adverse reactions. The release of SRS data may disclose the…

Remote user verification in Internet-based applications is becoming increasingly important nowadays. A popular scenario for it consists of submitting a picture of the user's Identity Document (ID) to a service platform, authenticating its…

Synthetic data has been widely applied in the real world recently. One typical example is the creation of synthetic data for privacy concerned datasets. In this scenario, synthetic data substitute the real data which contains the privacy…

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However,…

Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy and regulations. As a result, AI remains heavily underutilized in many of the most important domains, including healthcare, education,…