Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
扰动诱导线性化:仅使用线性分类器构造不可学习数据
机构 * Huazhong University of Science and Technology(华中科技大学)
AI总结 本文提出PIL方法,利用线性分类器生成扰动,以高效构建不可学习数据,减少计算成本并提升数据保护效果。
Comments This paper has been accepted to ICLR 2026