mlsanityData to 14 Oct 2026

SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data

arXiv 2404.15821 ↗First posted 24 Apr 2024cs.LG cs.PFcited by 27

Not on the map. Why?

Abstract (arXiv)

With the growing demand for synthetic data to address contemporary issues in machine learning, such as data scarcity, data fairness, and data privacy, having robust tools for assessing the utility and potential privacy risks of such data becomes crucial. SynthEval, a novel open-source evaluation framework distinguishes itself from existing tools by treating categorical and numerical attributes with equal care, without assuming any special kind of preprocessing steps. This~makes it applicable to virtually any synthetic dataset of tabular records. Our tool leverages statistical and machine learning techniques to comprehensively evaluate synthetic data fidelity and privacy-preserving integrity. SynthEval integrates a wide selection of metrics that can be used independently or in highly customisable benchmark configurations, and can easily be extended with additional metrics. In this paper, we describe SynthEval and illustrate its versatility with examples. The framework facilitates better benchmarking and more consistent comparisons of model capabilities.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 10 of its 49 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

10 of 49 references.

References · 10

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2019Modeling Tabular data using Conditional GANcited by 699
  3. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  4. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  5. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  6. 2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
  7. 2020Generating Electronic Health Records with Multiple Data Types and Constraintscited by 21
  8. 2020Relational Data Synthesis using Generative Adversarial Networks: A Design Space Explorationcited by 21
  9. 2022Permutation-Invariant Tabular Data Synthesiscited by 6
  10. 2020Deep generative models in DataSHIELDcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 16.

27 papers.

Sort:

By area:

  1. 2025Synthetic Tabular Data: Methods, Attacks and Defensescited by 9
  2. 2025Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation -- Extended Versioncited by 5
  3. 2025TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representationcited by 5
  4. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesiscited by 4
  5. 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Featurescited by 4
  6. 2026Improving TabPFN's Synthetic Data Generation by Integrating Causal Structurecited by 3
  7. 2025TABFAIRGDT: A Fast Fair Tabular Data Generator using Autoregressive Decision Treescited by 2
  8. 2026TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Datacited by 2
  9. 2025Privacy-Preserving Fair Synthetic Tabular Datacited by 1
  10. 2025SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generationcited by 1
  11. 2025Privacy-Preserving Synthetic Review Generation with Diverse Writing Styles Using LLMscited by 1
  12. 2025Disjoint Generation of Synthetic Datacited by 0
15 more
  1. 2025Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcitycited by 0
  2. 2025Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesiscited by 0
  3. 2026Generating High-quality Privacy-preserving Synthetic Datacited by 0
  4. 2026Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimatorscited by 0
  5. 2026Synthetic Tabular Generators Fail to Preserve Behavioral Fraud Patterns: A Benchmark on Temporal, Velocity, and Multi-Account Signalscited by 0
  6. 2026Evaluating quality in synthetic data generation for large tabular health datasetscited by 0
  7. 2026Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Trainingcited by 0
  8. 2026On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metricscited by 0
  9. 2026No Free Lunch for Synthetic Images under Data Scarcity Conditionscited by 0
  10. 2026Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmarkcited by 0
  11. 2026PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimizationcited by 0
  12. 2026Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Datacited by 0
  13. 2026K-IPO: Kendall-constrained Importance Preserving Oversampling for Imbalanced Tabular Datacited by 0
  14. 2026ProxyGuard: Direct Reliability Inference for Randomized Data Release Mechanisms with Shared Targetscited by 0
  15. 2026Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generationcited by 0