当先验知识失效：在预训练模型中不可学习示例的易受性
When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining
AI总结：
本文提出BAIT方法，通过双层优化机制有效对抗预训练先验对不可学习示例的干扰，保持数据不可学习性。
摘要：
不可学习示例（UEs）是一种数据保护策略，通过生成不可察觉的扰动来误导模型学习虚假相关性而非底层语义。在本文中，我们揭示了当学习从预训练模型开始时，UEs的一个根本性脆弱性。关键的是，我们的实证分析显示，即使数据通过精心设计的扰动进行保护，预训练先验仍然提供丰富的语义表示，使模型能够绕过UEs引入的捷径并捕捉真实特征，从而抵消不可学习性。为了解决这一问题，我们提出了BAIT（将人工扰动绑定到错误目标），一种新的双层优化公式。具体而言，内层旨在将扰动样本与真实标签关联起来，以模拟标准的数据-标签对齐，而外层则通过强制实施错误标签-扰动绑定，将样本映射到指定的错误目标。这种机制有效覆盖了先验的语义指导，迫使模型依赖于注入的扰动，从而防止获取真实语义。在标准基准和多个预训练骨干网络上的广泛实验表明，BAIT有效减轻了预训练先验的影响并保持了数据不可学习性。
英文摘要：
Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlying semantics. In this paper, we uncover a fundamental vulnerability of UEs that emerges when learning starts from a pretrained model. Crucially, our empirical analysis shows that even when data are protected by carefully crafted perturbations, pretraining priors still furnish rich semantic representations that allow the model to circumvent the shortcuts introduced by UEs and capture genuine features, thereby nullifying unlearnability. To address this, we propose BAIT (Binding Artificial perturbations to Incorrect Targets), a novel bi-level optimization formulation. Specifically, the inner level aims at associating the perturbed samples with real labels to simulate standard data-label alignment, while the outer level actively disrupts this alignment by enforcing a mislabel-perturbation binding that maps samples to designated incorrect targets. This mechanism effectively overrides the semantic guidance of priors, forcing the model to rely on the injected perturbations and consequently preventing the acquisition of true semantics. Extensive experiments on standard benchmarks and multiple pretrained backbones demonstrate that BAIT effectively mitigates the influence of pretraining priors and maintains data unlearnability.
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。
