UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917262500298752 |
|---|---|
| author | He, Jiaming Luo, Fuming Li, Hongwei Jiang, Wenbo Fan, Wenshu Shi, Zhenbo Jiang, Xudong Yu, Yi |
| author_facet | He, Jiaming Luo, Fuming Li, Hongwei Jiang, Wenbo Fan, Wenshu Shi, Zhenbo Jiang, Xudong Yu, Yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07358 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding He, Jiaming Luo, Fuming Li, Hongwei Jiang, Wenbo Fan, Wenshu Shi, Zhenbo Jiang, Xudong Yu, Yi Machine Learning 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. |
| title | UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.07358 |