论文标题
关于公用网络基于神经网络的私人表格培训数据合成器的公用事业恢复能力在隐私放松下
On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation
论文作者
论文摘要
在实践中，为审核生成模型隐私 - 实用性权衡做出审计的程序是一个重要但尚未解决的问题。现有作品集中于在综合数据训练中对综合范式进行综合测试，研究火车效力降解的隐私限制副作用。我们通过观察隐私管制副作用对合成培训数据实用程序的副作用，将对隐私 - 实用性权衡的理解推向了下一个水平。令人惊讶的是，我们发现在隐私管制下，DP-CTGAN和PATE-CTGAN的公用事业恢复能力无能为力，从而引起了对其实际应用的担忧。主要信息是隐私放松管制并不总是意味着实用性恢复。
Devising procedures for auditing generative model privacy-utility tradeoff is an important yet unresolved problem in practice. Existing works concentrates on investigating the privacy constraint side effect in terms of utility degradation of the train on synthetic, test on real paradigm of synthetic data training. We push such understanding on privacy-utility tradeoff to next level by observing the privacy deregulation side effect on synthetic training data utility. Surprisingly, we discover the Utility Recovery Incapability of DP-CTGAN and PATE-CTGAN under privacy deregulation, raising concerns on their practical applications. The main message is Privacy Deregulation does NOT always imply Utility Recovery.
