论文标题
私人一代小图像
Differentially Private Generation of Small Images
论文作者
论文摘要
我们探讨了具有不同隐私对匿名图像数据集的生成对抗网络的培训。在MNIST上，我们使用参数从$ε$ - $δ$差异隐私和创建分数来衡量隐私 - 实用性权衡。我们的实验揭示了饱和的培训制度，在该制度中，增加的隐私预算几乎没有增加生成图像的质量。我们还可以通过分析解释为什么差异化私有ADAM优化独立于梯度剪辑参数。此外，我们在以前的私人深度学习方面突出了常见的错误，我们在最近的文献中发现了这些错误。在对主题的整个治疗过程中，我们希望预防将来对匿名性的错误估计。
We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from $ε$-$δ$ differential privacy and the inception score. Our experiments uncover a saturated training regime where an increasing privacy budget adds little to the quality of generated images. We also explain analytically why differentially private Adam optimization is independent of the gradient clipping parameter. Furthermore, we highlight common errors in previous works on differentially private deep learning, which we uncovered in recent literature. Throughout the treatment of the subject, we hope to prevent erroneous estimates of anonymity in the future.
