Related papers: Privacy Amplification for Synthetic data using Ran…

Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via…

The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and…

The shuffle model of Differential Privacy (DP) has gained significant attention in privacy-preserving data analysis due to its remarkable tradeoff between privacy and utility. It is characterized by adding a shuffling procedure after each…

Metric Differential Privacy (mDP) extends the local differential privacy (LDP) framework to metric spaces, enabling more nuanced privacy protection for data such as geo-locations. However, existing mDP optimization methods, particularly…

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

Differential privacy (DP) is a mathematical privacy notion increasingly deployed across government and industry. With DP, privacy protections are probabilistic: they are bounded by the privacy budget parameter, $\epsilon$. Prior work in…

Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this…

Statistical data anonymization increasingly relies on fully synthetic microdata, for which classical identity disclosure measures are less informative than an adversary's ability to infer sensitive attributes from released data. We…

This paper proposes and compares measures of identity and attribute disclosure risk for synthetic data. Data custodians can use the methods proposed here to inform the decision as to whether to release synthetic versions of confidential…

Differential privacy (DP) provides a principled approach to synthesizing data (e.g., loads) from real-world power systems while limiting the exposure of sensitive information. However, adversaries may exploit synthetic data to calibrate…

Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We…

Protecting user data privacy can be achieved via many methods, from statistical transformations to generative models. However, all of them have critical drawbacks. For example, creating a transformed data set using traditional techniques is…

Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…

Differential privacy (DP) provides a mathematical guarantee limiting what an adversary can learn about any individual from released data. However, achieving this protection typically requires adding noise, and noise can accumulate when many…

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using…

Synthetic data generation is gaining traction as a privacy enhancing technology (PET). When properly generated, synthetic data preserve the analytic utility of real data while avoiding the retention of information that would allow the…

Synthetic data is often presented as a method for sharing sensitive information in a privacy-preserving manner by reproducing the global statistical properties of the original data without disclosing sensitive information about any…

Pseudonymisation provides the means to reduce the privacy impact of monitoring, auditing, intrusion detection, and data collection in general on individual subjects. Its application on data records, especially in an environment with…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to…