论文标题
MIXCON：调整数据表示的可分离性，以使其硬数据恢复
MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
论文作者
论文摘要
为了解决深层神经网络（DNN）容易受到模型反演攻击的影响，我们设计了一个目标函数，该功能调整了隐藏数据表示的可分离性，以控制数据实用性与反转攻击脆弱性之间的权衡。我们的方法是由神经网络培训中数据可分离性的理论见解以及模型反转的硬度的结果所激发的。从经验上讲，通过调整数据表示的可分离性，我们表明数据可分离性存在甜点，因此在维持数据实用程序的同时很难在推理过程中恢复数据。
To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data representations, as a way to control the trade-off between data utility and vulnerability to inversion attacks. Our method is motivated by the theoretical insights of data separability in neural networking training and results on the hardness of model inversion. Empirically, by adjusting the separability of data representation, we show that there exist sweet-spots for data separability such that it is difficult to recover data during inference while maintaining data utility.
