相关论文: Understanding the Impact of Data Domain Extraction…

Membership Inference Attacks (MIAs) have emerged as a principled framework for auditing the privacy of synthetic data generated by tabular generative models, where many diverse methods have been proposed that each exploit different privacy…

Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that…

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the…

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…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

When acting as a privacy-enhancing technology, synthetic data generation (SDG) aims to maintain a resemblance to the real data while excluding personally-identifiable information. Many SDG algorithms provide robust differential privacy (DP)…

Membership inference attacks (MIAs) pose significant privacy risks by determining whether individual data is in a dataset. While differential privacy (DP) mitigates these risks, it has limitations including limited resolution in expressing…

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn,…

A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs,…

Tabular data typically contains private and important information; thus, precautions must be taken before they are shared with others. Although several methods (e.g., differential privacy and k-anonymity) have been proposed to prevent…

Tabular Generative Models are often argued to preserve privacy by creating synthetic datasets that resemble training data. However, auditing their empirical privacy remains challenging, as commonly used similarity metrics fail to…

Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To address this, differentially private synthetic data generation…

To address the scarcity and privacy concerns of network traffic data, various generative models have been developed to produce synthetic traffic. However, synthetic traffic is not inherently privacy-preserving, and the extent to which it…

Tabular data sharing under privacy constraints is increasingly important for research and collaboration. Synthetic data generators (SDGs) are a promising solution, but synthetic data remains vulnerable to attacks, such as membership…

Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…

Synthetic data generation (SDG) has become increasingly popular as a privacy-enhancing technology. It aims to maintain important statistical properties of its underlying training data, while excluding any personally identifiable…

Techniques to deliver privacy-preserving synthetic datasets take a sensitive dataset as input and produce a similar dataset as output while maintaining differential privacy. These approaches have the potential to improve data sharing and…

Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become the standard approach to evaluate the privacy risk of…

Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely on heuristics and unrealistic assumptions about model access, offering limited ability to…