UTOPIA: 通过解耦的快捷嵌入实现不可学习的表格数据
UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding
AI总结：
UTOPIA通过解耦的快捷嵌入方法，实现对敏感表格数据的不可学习保护，有效阻止未经授权的模型训练。
摘要：
不可学习的例子（UE）已作为一种实用机制出现，用于防止未经授权在私有视觉数据上训练模型，而将其扩展到表格数据则具有挑战性。金融和医疗领域的表格数据高度敏感，但现有UE方法效果不佳，因为表格特征混合了数值和分类约束，并表现出显著性稀疏性，学习主要由少数维度主导。在谱主导条件下，我们证明当毒谱主导清洁语义谱时，可以实现认证的不可学习性。基于此，我们提出通过解耦的快捷嵌入实现不可学习的表格数据（UTOPIA），利用特征冗余将优化解耦为两个通道：高显著性特征用于语义混淆，低显著性冗余特征用于嵌入超相关的快捷路径，从而产生具有约束意识的主导快捷路径，同时保持表格的有效性。在广泛的表格数据集和模型上进行的广泛实验表明，UTOPIA使未经授权的训练接近随机性能，优于强大的UE基线，并在不同架构之间具有良好的转移性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
