论文标题
输入属性如何影响差异隐私的隐私损失？
How Do Input Attributes Impact the Privacy Loss in Differential Privacy?
论文作者
论文摘要
差异隐私（DP）通常是对数据库中所有个人的最坏案例隐私保证。最近，引入了对个别受试者或其属性的扩展。在单个/综合DP解释下，我们研究了DP神经网络中的每受试者梯度规范与个人隐私损失之间的联系，并引入了一种新的指标，称为隐私损失输入易感性（PLIS），这使一个人可以将受试者的隐私损失分配给其输入属性。我们通过实验表明这如何识别敏感属性和具有数据重建风险的受试者。
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database. More recently, extensions to individual subjects or their attributes, have been introduced. Under the individual/per-instance DP interpretation, we study the connection between the per-subject gradient norm in DP neural networks and individual privacy loss and introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS), which allows one to apportion the subject's privacy loss to their input attributes. We experimentally show how this enables the identification of sensitive attributes and of subjects at high risk of data reconstruction.
