Robust Detection of Synthetic Tabular Data under Schema Variability
By: G. Charbel N. Kindji , Elisa Fromont , Lina Maria Rojas-Barahona and more
Potential Business Impact:
Finds fake computer-made tables in real data.
The rise of powerful generative models has sparked concerns over data authenticity. While detection methods have been extensively developed for images and text, the case of tabular data, despite its ubiquity, has been largely overlooked. Yet, detecting synthetic tabular data is especially challenging due to its heterogeneous structure and unseen formats at test time. We address the underexplored task of detecting synthetic tabular data in the wild, where tables have variable and previously unseen schemas. We introduce a novel datum-wise transformer architecture that significantly outperforms the only previously published baseline, improving both AUC and accuracy by 7 points. By incorporating a table-adaptation component, our model gains an additional 7 accuracy points, demonstrating enhanced robustness. This work provides the first strong evidence that detecting synthetic tabular data in real-world conditions is not only feasible, but can be done with high reliability.
Similar Papers
Datum-wise Transformer for Synthetic Tabular Data Detection in the Wild
Machine Learning (CS)
Finds fake computer-made tables of information.
Synthetic Tabular Data Detection In the Wild
Machine Learning (CS)
Finds fake computer spreadsheets, even new kinds.
Assessing Generative Models for Structured Data
Machine Learning (CS)
Makes fake data that looks like real data.