Deep learning models are often trained on data sets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this article, we consider a recently proposed privacy definition termed f -differential privacy (Dong, Roth, et al., 2019) for a refined privacy analysis of training neural networks. Leveraging the appealing properties of f -differential privacy in handling composition and subsampling, this article derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as Abadi et al. ( 2016) did. Our results demonstrate that the f -differential privacy framework allows for a new privacy analysis that improves on the prior analysis (Abadi et al., 2016), which in turn suggests tuning certain parameters of neural networks for a better prediction accuracy without violating the privacy budget. These theoretically derived improvements are confirmed by our experiments in a range of tasks in image classification, text classification, and recommender systems. Python code to calculate the privacy cost for these experiments is publicly available in the TensorFlow Privacy library.

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this paper, we consider a recently proposed privacy definition termed f -differential privacy [17] for a refined privacy analysis of training neural networks. Leveraging the appealing properties of f -differential privacy in handling composition and subsampling, this paper derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as [3] did. Our results demonstrate that the f -differential privacy framework allows for a new privacy analysis that improves on the prior analysis [3], which in turn suggests tuning certain parameters of neural networks for a better prediction accuracy without violating the privacy budget. These theoretically derived improvements are confirmed by our experiments in a range of tasks in image classification, text classification, and recommender systems.

No abstract

In deep learning with differential privacy (DP), the neural network achieves the privacy usually at the cost of slower convergence (and thus lower performance) than its non-private counterpart. This work gives the first convergence analysis of the DP deep learning, through the lens of training dynamics and the neural tangent kernel (NTK). Our convergence theory successfully characterizes the effects of two key components in the DP training: the per-sample clipping (flat or layerwise) and the noise addition. Our analysis not only initiates a general principled framework to understand the DP deep learning with any network architecture and loss function, but also motivates a new clipping method -the global clipping, that significantly improves the convergence while preserving the same privacy guarantee as the existing local clipping.In terms of theoretical results, we establish the precise connection between the per-sample clipping and NTK matrix. We show that in the gradient flow, i.e., with infinitesimal learning rate, the noise level of DP optimizers does not affect the convergence. We prove that DP gradient descent (GD) with global clipping guarantees the monotone convergence to zero loss, which can be violated by the existing DP-GD with local clipping. Notably, our analysis framework easily extends to other optimizers, e.g., DP-Adam. Empirically speaking, DP optimizers equipped with global clipping perform strongly on a wide range of classification and regression tasks. In particular, our global clipping is surprisingly effective at learning calibrated classifiers, in contrast to the existing DP classifiers which are oftentimes over-confident and unreliable. Implementation-wise, the new clipping can be realized by adding one line of code into the Opacus library.