Tabular foundation models can reveal if a dataset trained them

Dataset Inference for Data Provenance and Privacy Auditing in Tabular Foundation Models

Machine Learning

Summary

Tabular foundation models are trained on many datasets, sometimes including private data, but it's hard to know which datasets were used. The authors created a method to check if a particular dataset was included in the training of such a model by probing the model and combining different clues. This method can identify dataset usage with high accuracy for various models on real-world tabular data. Their study also shows what factors affect this ability, helping with privacy checks and verifying proprietary data use.

What this means in practice

  • For privacy audit teams: Detect private or proprietary tabular datasets included in foundation model training via dataset inference.
  • For data compliance officers: Verify compliance by identifying whether regulated datasets were used to train commercial tabular models.

Authors

Dariush Wahdany, Jesse Cresswell, Naiqing Guan, Atiyeh Ashari Ghomi, Franziska Boenisch, Adam Dziedzic

Abstract

Tabular foundation models (TFMs) are increasingly deployed through black-box APIs and trained on large collections of real-world tabular datasets. As this training paradigm becomes more widely adopted, private or proprietary datasets may be incorporated into pre-training corpora, yet there are currently no dedicated methods for determining whether a given tabular dataset was used to train a TFM. As a solution, we introduce the first dataset inference method for TFMs, aiming to infer whether a suspect dataset was part of a model's pre-training data. We systematically analyze a broad collection of candidate signals that can be observed from a black-box TFM via input manipulation and find that individual signals provide only weak evidence of training data membership. However, by combining multiple complementary signals, we can infer dataset membership for several state-of-the-art TFMs trained on real tabular data, achieving up to 0.99 ROCAUC dependent on the TFM. We then study factors that influence dataset identification, including pre-training data composition, model capacity, and the use of real vs. synthetic data. Our results show that our dataset inference method is a practical auditing tool for detecting privacy leakage and the use of proprietary datasets in TFMs.