We present an approach to quantify and compare the privacy-accuracy trade-off for differentially private Variational Autoencoders. Our work complements previous work in two aspects. First, we evaluate the the strong reconstruction MI attack against Variational Autoencoders under differential privacy. Second, we address the data scientist's challenge of setting privacy parameter epsilon, which steers the differential privacy strength and thus also the privacy-accuracy trade-off. In our experimental study we consider image and time series data, and three local and central differential privacy mechanisms. We find that the privacy-accuracy trade-offs strongly depend on the dataset and model architecture. We do rarely observe favorable privacy-accuracy trade-off for Variational Autoencoders, and identify a case where LDP outperforms CDP.
翻译:我们提出了一个方法来量化和比较不同私人变式自动编码器的隐私-准确性权衡。我们的工作在两个方面补充了先前的工作。首先,我们评估了对不同隐私下的变式自动编码器的强力重建MI攻击。第二,我们处理数据科学家的挑战,即设置隐私参数Epsilon,该参数指导着不同的隐私强度,从而也指导着隐私-准确性权衡。在我们的实验研究中,我们考虑的是图像和时间序列数据,以及三个地方和中央差异性隐私机制。我们发现,隐私的准确性权衡在很大程度上取决于数据集和模型结构。我们很少为变式自动编码器看到有利的隐私-准确性交易,并找出一个LDP优于CDP的案例。