UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding

TL;DR

This paper introduces UTOPIA, a novel method for creating unlearnable tabular data by decoupling features to prevent unauthorized model training, especially in sensitive domains like finance and healthcare.

Contribution

UTOPIA is the first approach to effectively generate unlearnable tabular data by leveraging feature redundancy and spectral dominance, improving transferability and robustness.

Findings

UTOPIA achieves near-random performance in unauthorized training scenarios.

It outperforms existing unlearnable example baselines on various tabular datasets.

UTOPIA maintains tabular data validity while embedding effective shortcuts.

Abstract

Unlearnable examples (UE) have emerged as a practical mechanism to prevent unauthorized model training on private vision data, while extending this protection to tabular data is nontrivial. Tabular data in finance and healthcare is highly sensitive, yet existing UE methods transfer poorly because tabular features mix numerical and categorical constraints and exhibit saliency sparsity, with learning dominated by a few dimensions. Under a Spectral Dominance condition, we show certified unlearnability is feasible when the poison spectrum overwhelms the clean semantic spectrum. Guided by this, we propose Unlearnable Tabular Data via DecOuPled Shortcut EmbeddIng (UTOPIA), which exploits feature redundancy to decouple optimization into two channels: high saliency features for semantic obfuscation and low saliency redundant features for embedding a hyper correlated shortcut, yielding constraint-aware dominant shortcuts while preserving tabular validity. Extensive experiments across tabular datasets and models show UTOPIA drives unauthorized training toward near random performance, outperforming strong UE baselines and transferring well across architectures.