# Cross-table Synthetic Tabular Data Detection

arXiv: https://arxiv.org/abs/2412.13227 · HTML: https://mlsanity.com/paper/2412.13227/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 22 of 22)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [What Algorithms can Transformers Learn? A Study in Length Generalization](https://mlsanity.com/paper/2310.16028/) (2023)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [Benchmarking Distribution Shift in Tabular Data with TableShift](https://mlsanity.com/paper/2312.07577/) (2023)
- [FinDiff: Diffusion Models for Financial Tabular Data Generation](https://mlsanity.com/paper/2309.01472/) (2023)
- [Deepfake Videos in the Wild: Analysis and Detection](https://mlsanity.com/paper/2103.04263/) (2021)
- [Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks](https://mlsanity.com/paper/2210.00400/) (2022)
- [Robust AI-Generated Text Detection by Restricted Embeddings](https://mlsanity.com/paper/2410.08113/) (2024)
- [Deep Learning in the Wild](https://mlsanity.com/paper/1807.04950/) (2018)

## Abstract (arXiv)

Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores whether synthetic tabular data can be reliably identified ''in the wild''-meaning across different generators, domains, and table formats. This challenge is unique to tabular data, where structures (such as number of columns, data types, and formats) can vary widely from one table to another. We propose three cross-table baseline detectors and four distinct evaluation protocols, each corresponding to a different level of ''wildness''. Our very preliminary results confirm that cross-table adaptation is a challenging task.