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 inference attacks (MIAs), which aim to determine whether a specific record was part of the training data. State-of-the-art MIAs are powerful but impractical: they rely on shadow modeling, requiring hundreds of SDG training runs, and need auxiliary data several times larger than the original training set. Fast proxy metrics like distance to closest record (DCR) are efficient but have limited sensitivity to MIA risk. We introduce ReMIA (Relative Membership Inference Attack), a practical privacy metric that requires only two SDG training runs and additional data no larger than the original training set. Rather than predicting whether a record was in the training set, ReMIA generates two synthetic datasets from two source datasets and measures whether a classifier can identify which source a record came from. Experiments across multiple tabular datasets and SDGs show that ReMIA has a sensitivity comparable to state-of-the-art MIAs while being substantially more practical. We further observe that SDGs can achieve privacy-utility trade-offs that traditional noise-based anonymization methods do not match. Code is available at https://github.com/aindo-com/remia.
TVineSynth: A Truncated C-Vine Copula Generator of Synthetic Tabular Data to Balance Privacy and Utility
Norwegian Computing Center(挪威计算中心);University of Oslo(奥斯陆大学);Technical University of Munich(慕尼黑工业大学);Munich Data Science Institute(慕尼黑数据科学研究所);Integreat - Norwegian Centre for Knowledge-driven Machine Learning(Integreat——挪威知识驱动型机器学习中心)
When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
Department of Mathematical Sciences University of Texas at El Paso(数学科学系德克萨斯理工大学埃尔帕索分校);Department of Computer Science University of Texas at El Paso(计算机科学系德克萨斯理工大学埃尔帕索分校);Department of Radiology St. Jude Children’s Research Hospital(放射医学系圣犹太儿童研究医院)
A Reinforcement Learning Approach to Synthetic Data Generation
Department of Computer Science, Princeton University(普林斯顿大学计算机科学系);Department of Biomedical Informatics, Vanderbilt University Medical Center(范德比尔特大学医学中心生物医学信息学系);Department of Biostatistics, Vanderbilt University Medical Center(范德比尔特大学医学中心生物统计学系);Department of Computer Science, Vanderbilt University(范德比尔特大学计算机科学系);John F. Hardesty Department of Ophthalmology and Visual Sciences, Washington University(华盛顿大学约翰·F·哈里斯德眼科学与视觉科学系)