Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent (DPSGD) is the most popular training method with differential privacy in image recognition. However, existing DPSGD schemes lead to significant performance degradation, which prevents the application of differential privacy. In this paper, we propose a simulated annealing-based differentially private stochastic gradient descent scheme (SA-DPSGD) which accepts a candidate update with a probability that depends both on the update quality and on the number of iterations. Through this random update screening, we make the differentially private gradient descent proceed in the right direction in each iteration, and result in a more accurate model finally. In our experiments, under the same hyperparameters, our scheme achieves test accuracies 98.35%, 87.41% and 60.92% on datasets MNIST, FashionMNIST and CIFAR10, respectively, compared to the state-of-the-art result of 98.12%, 86.33% and 59.34%. Under the freely adjusted hyperparameters, our scheme achieves even higher accuracies, 98.89%, 88.50% and 64.17%. We believe that our method has a great contribution for closing the accuracy gap between private and non-private image classification.

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model parameters, such as deep neural network model weights. Recently, differential privacy has been applied to federated learning to protect data privacy, but the noise added may degrade the learning performance much. Typically, in previous work, training parameters were clipped equally and noises were added uniformly. The heterogeneity and convergence of training parameters were simply not considered. In this paper, we propose a differentially private scheme for federated learning with adaptive noise (Adap DP-FL). Specifically, due to the gradient heterogeneity, we conduct adaptive gradient clipping for different clients and different rounds; due to the gradient convergence, we add decreasing noises accordingly. Extensive experiments on real-world datasets demonstrate that our Adap DP-FL outperforms previous methods significantly.

梯度泄漏攻击被认为是深度学习中的邪恶隐私威胁之一，因为攻击者在迭代培训期间隐蔽了梯度更新，而不会影响模型培训质量，但又使用泄漏的梯度逐步重建敏感培训数据，具有高攻击成功率。虽然具有差异隐私的深度学习是发布具有差异隐私保障的深度学习模型的违法标准，但我们展示了具有固定隐私参数的差异私有算法易受梯度泄漏攻击的影响。本文调查了差异隐私（DP）的梯度泄漏弹性深度学习的替代方法。首先，我们分析了差异隐私的深度学习的现有实现，它使用固定噪声方差使用固定隐私参数将恒定噪声对所有层中的梯度注入恒定噪声。尽管提供了DP保证，但该方法遭受了低精度，并且很容易受到梯度泄漏攻击。其次，通过使用动态隐私参数，我们提出了一种梯度泄漏弹性深度学习方法，差异隐私保证。与导致恒定噪声方差导致的固定参数策略不同，不同的动态参数策略存在替代技术，以引入自适应噪声方差和自适应噪声注入，其与差别私有模型训练期间的梯度更新的趋势紧密对齐。最后，我们描述了四个互补指标来评估和比较替代方法。

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy. Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality. * Google.† OpenAI. Work done while at Google.

深度神经网络（DNNS）铰接对大型数据集的可用性的最新成功;但是，对此类数据集的培训经常为敏感培训信息构成隐私风险。在本文中，我们的目标是探讨生成模型和梯度稀疏性的力量，并提出了一种可扩展的隐私保留生成模型数据标准。与标准展示隐私保留框架相比，允许教师对一维预测进行投票，在高维梯度向量上投票在隐私保存方面具有挑战性。随着需要尺寸减少技术，我们需要在（1）之间的改进之间导航精致的权衡空间，并进行SGD收敛的放缓。为了解决这一点，我们利用通信高效学习，并通过将顶-K压缩与相应的噪声注入机构相结合，提出一种新的噪声压缩和聚集方法TopAGG。理论上，我们证明了DataLens框架保证了其生成数据的差异隐私，并提供了其收敛性的分析。为了展示DataLens的实际使用情况，我们对不同数据集进行广泛的实验，包括Mnist，Fashion-Mnist和高维Celeba，并且我们表明，DataLens显着优于其他基线DP生成模型。此外，我们改进了所提出的Topagg方法，该方法是DP SGD培训的主要构建块之一，并表明它能够在大多数情况下实现比最先进的DP SGD方法更高的效用案件。我们的代码在HTTPS://github.com/ai-secure/datalens公开提供。

Privacy in AI remains a topic that draws attention from researchers and the general public in recent years. As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use differential privacy (DP). To achieve DP in the learning process, existing algorithms typically limit the magnitude of gradients with a constant clipping, which requires carefully tuned due to its significant impact on model performance. As a solution to this issue, latest works NSGD and Auto-S innovatively propose to use normalization instead of clipping to avoid hyperparameter tuning. However, normalization-based approaches like NSGD and Auto-S rely on a monotonic weight function, which imposes excessive weight on small gradient samples and introduces extra deviation to the update. In this paper, we propose a Differentially Private Per-Sample Adaptive Clipping (DP-PSAC) algorithm based on a non-monotonic adaptive weight function, which guarantees privacy without the typical hyperparameter tuning process of using a constant clipping while significantly reducing the deviation between the update and true batch-averaged gradient. We provide a rigorous theoretical convergence analysis and show that with convergence rate at the same order, the proposed algorithm achieves a lower non-vanishing bound, which is maintained over training iterations, compared with NSGD/Auto-S. In addition, through extensive experimental evaluation, we show that DP-PSAC outperforms or matches the state-of-the-art methods on multiple main-stream vision and language tasks.

我们考虑一个顺序设置，其中使用单个数据集用于执行自适应选择的分析，同时确保每个参与者的差别隐私丢失不超过预先指定的隐私预算。此问题的标准方法依赖于限制所有个人对所有个人的隐私损失的最坏情况估计，以及每个单一分析的所有可能的数据值。然而，在许多情况下，这种方法过于保守，特别是对于“典型”数据点，通过参与大部分分析产生很少的隐私损失。在这项工作中，我们基于每个分析中每个人的个性化隐私损失估计的价值，给出了更严格的隐私损失会计的方法。实现我们设计R \'enyi差异隐私的过滤器。过滤器是一种工具，可确保具有自适应选择的隐私参数的组合算法序列的隐私参数不超过预先预算。我们的过滤器比以往的$（\ epsilon，\ delta）$ - rogers等人的差别隐私更简单且更紧密。我们将结果应用于对嘈杂渐变下降的分析，并显示个性化会计可以实用，易于实施，并且只能使隐私式权衡更紧密。

A major direction in differentially private machine learning is differentially private fine-tuning: pretraining a model on a source of "public data" and transferring the extracted features to downstream tasks. This is an important setting because many industry deployments fine-tune publicly available feature extractors on proprietary data for downstream tasks. In this paper, we use features extracted from state-of-the-art open source models to solve benchmark tasks in computer vision and natural language processing using differentially private fine-tuning. Our key insight is that by accelerating training, we can quickly drive the model parameters to regions in parameter space where the impact of noise is minimized. In doing so, we recover the same performance as non-private fine-tuning for realistic values of epsilon in [0.01, 1.0] on benchmark image classification datasets including CIFAR100.

差异隐私（DP）提供了正式的隐私保证，以防止对手可以访问机器学习模型，从而从提取有关单个培训点的信息。最受欢迎的DP训练方法是差异私有随机梯度下降（DP-SGD），它通过在训练过程中注入噪声来实现这种保护。然而，以前的工作发现，DP-SGD通常会导致标准图像分类基准的性能显着降解。此外，一些作者假设DP-SGD在大型模型上固有地表现不佳，因为保留隐私所需的噪声规范与模型维度成正比。相反，我们证明了过度参数化模型上的DP-SGD可以比以前想象的要好得多。将仔细的超参数调整与简单技术结合起来，以确保信号传播并提高收敛速率，我们获得了新的SOTA，而没有额外数据的CIFAR-10，在81.4％的81.4％下（8，10^{ - 5}） - 使用40 -layer wide-Resnet，比以前的SOTA提高了71.7％。当对预训练的NFNET-F3进行微调时，我们在ImageNet（0.5，8*10^{ - 7}）下达到了83.8％的TOP-1精度。此外，我们还在（8，8 \ cdot 10^{ - 7}）下达到了86.7％的TOP-1精度，DP仅比当前的非私人SOTA仅4.3％。我们认为，我们的结果是缩小私人图像分类和非私有图像分类之间准确性差距的重要一步。

Privacy noise may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive optimization. In this work, we explore techniques to estimate and efficiently adapt to gradient geometry in private adaptive optimization without auxiliary data. Motivated by the observation that adaptive methods can tolerate stale preconditioners, we propose differentially private adaptive training with delayed preconditioners (DP^2), a simple method that constructs delayed but less noisy preconditioners to better realize the benefits of adaptivity. Theoretically, we provide convergence guarantees for our method for both convex and non-convex problems, and analyze trade-offs between delay and privacy noise reduction. Empirically, we explore DP^2 across several real-world datasets, demonstrating that it can improve convergence speed by as much as 4x relative to non-adaptive baselines and match the performance of state-of-the-art optimization methods that require auxiliary data.

HyperParameter优化是机器学习中的一种无处不在的挑战，训练型模型的性能在其有效选择时依赖于大致依赖。虽然为此目的存在丰富的工具，但目前在差分隐私（DP）的约束下，目前没有实际的超参数选择方法。我们研究鉴于差异私立机器学习的诚实的封锁，其中，在整体隐私预算中占了超代调优的过程。为此，我们）显示标准的组合工具在许多设置中优于更高级的技术，ii）经验和理论上展示了学习率和剪辑规范率HyperParameters，III之间的内在联系，表明DPADAM等自适应优化器享有显着的优势在诚实的HyperParameter调整过程中，IV）借鉴了DP设置中ADAM的新颖限制行为，以设计新的更高效的优化器。

差异私有随机梯度下降（DPSGD）是基于差分隐私（DP）范例的随机梯度下降的变化，这可以减轻来自在训练数据中存在敏感信息的隐私威胁。然而，具有DPSGD的培训深度神经网络的一个主要缺点是模型精度的降低。本文研究了标准化层对DPSGD性能的影响。我们证明标准化层显着影响了深度神经网络与嘈杂参数的效用，应该被视为DPSGD培训的基本成分。特别是，我们提出了一种新的方法，用于将批量标准化与DPSGD集成，而不会产生额外的隐私损失。通过我们的方法，我们能够培训更深的网络并实现更好的效用隐私权衡。

提出测试释放（PTR）是一个差异隐私框架，可符合局部功能的敏感性，而不是其全球敏感性。该框架通常用于以差异性私有方式释放强大的统计数据，例如中位数或修剪平均值。尽管PTR是十年前引入的常见框架，但在诸如Robust SGD之类的应用程序中使用它，我们需要许多自适应鲁棒的查询是具有挑战性的。这主要是由于缺乏Renyi差异隐私（RDP）分析，这是一种瞬间的私人深度学习方法的基础。在这项工作中，我们概括了标准PTR，并在目标函数界定全局灵敏度时得出了第一个RDP。我们证明，与直接分析的$（\ eps，\ delta）$ -DP相比，我们的RDP绑定的PTR可以得出更严格的DP保证。我们还得出了亚采样下PTR的算法特异性隐私扩增。我们表明，我们的界限比一般的上限和接近下限的界限要紧密得多。我们的RDP界限可以为PTR的许多自适应运行的组成而更严格的隐私损失计算。作为我们的分析的应用，我们表明PTR和我们的理论结果可用于设计私人变体，用于拜占庭强大的训练算法，这些变体使用可靠的统计数据用于梯度聚集。我们对不同数据集和体系结构的标签，功能和梯度损坏的设置进行实验。我们表明，与基线相比，基于PTR的私人和强大的培训算法可显着改善该实用性。

我们考虑使用迷你批量梯度进行差异隐私（DP）的培训模型。现有的最先进的差异私有随机梯度下降（DP-SGD）需要通过采样或洗机来获得最佳隐私/准确性/计算权衡的隐私放大。不幸的是，在重要的实际情况下，精确采样和洗牌的精确要求可能很难获得，特别是联邦学习（FL）。我们设计和分析跟随 - 正规的领导者（DP-FTRL）的DP变体，其比较（理论上和经验地）与放大的DP-SGD相比，同时允许更灵活的数据访问模式。DP-FTRL不使用任何形式的隐私放大。该代码可在https://github.com/google-Research/federated/tree/master/dp_ftrl和https://github.com/google-reesearch/dp-ftrl处获得。

当适用于大规模学习问题时，由于与差异性的性能下降和高记忆开销相比，所谓的隐私私人随机梯度下降（DP-SGD）的常规智慧已经满足了有限的成功。非隐私对应。我们展示了如何通过用新型DP正向传播（DP-FP）替换DP-SGD来减轻性能下降，然后是一个离上的非DP优化器。我们的DP-FP采用新的（1）表示剪辑，然后在前向传播阶段进行噪声，以及（2）微批量构建通过分置，以实现DP放大，并将噪声功率降低至1 / m $，其中$ m $是一步中的微批次数量。在培训分类模型时，我们的DP-FP与表示的所有隐私保留操作的DP-FP无天然偏离偏差，总噪声与模型大小，以及DP-SGD中的内存问题。结果，我们的DP-FP优于尖端DP-SGD，同时保持相同的隐私水平，并且它接近非私有基线，显着优于最先进的DP-SGD变体。例如，当在四个下游任务上应用于Roberta-Light时，DP-FP的平均准确性为91.34 \％，隐私预算小于3，代表了最先进的DP的3.81 \％的性能改进 - 与非私有基线相比，SGD和只有0.9 \％的损失，但具有明显降低的隐私泄漏风险。

Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern. An effective solution to this problem is to train models with differential privacy, which provides rigorous privacy guarantees by injecting random noise to the gradients. This paper focuses on the scenario where sensitive data are distributed among multiple participants, who jointly train a model through federated learning (FL), using both secure multiparty computation (MPC) to ensure the confidentiality of each gradient update, and differential privacy to avoid data leakage in the resulting model. A major challenge in this setting is that common mechanisms for enforcing DP in deep learning, which inject real-valued noise, are fundamentally incompatible with MPC, which exchanges finite-field integers among the participants. Consequently, most existing DP mechanisms require rather high noise levels, leading to poor model utility. Motivated by this, we propose Skellam mixture mechanism (SMM), an approach to enforce DP on models built via FL. Compared to existing methods, SMM eliminates the assumption that the input gradients must be integer-valued, and, thus, reduces the amount of noise injected to preserve DP. Further, SMM allows tight privacy accounting due to the nice composition and sub-sampling properties of the Skellam distribution, which are key to accurate deep learning with DP. The theoretical analysis of SMM is highly non-trivial, especially considering (i) the complicated math of differentially private deep learning in general and (ii) the fact that the mixture of two Skellam distributions is rather complex, and to our knowledge, has not been studied in the DP literature. Extensive experiments on various practical settings demonstrate that SMM consistently and significantly outperforms existing solutions in terms of the utility of the resulting model.

我们审查在机器学习（ML）中使用差异隐私（DP）对隐私保护的使用。我们表明，在维护学习模型的准确性的驱动下，基于DP的ML实现非常宽松，以至于它们不提供DP的事前隐私保证。取而代之的是，他们提供的基本上是与传统（经常受到批评的）统计披露控制方法相似的噪声。由于缺乏正式的隐私保证，因此所提供的实际隐私水平必须经过实验评估，这很少进行。在这方面，我们提出的经验结果表明，ML中的标准反拟合技术可以比DP实现更好的实用性/隐私/效率权衡。

差异私有随机梯度下降（DP-SGD）通过在SGD训练期间将噪声添加到剪切梯度以满足差异隐私（DP）定义来防止训练数据隐私泄露。另一方面，跨越训练步骤的相同剪辑操作和附加噪声导致不稳定的更新甚至是增值时间，这显着降低了模型的准确性。在本文中，我们延长了高斯DP中央极限定理，以分别校准每个单独的步骤的剪切值和噪声功率。因此，我们能够提出动态DP-SGD，其在更新期间具有比DP-SGD更低的隐私成本，直到它们在目标更新数量达到相同的目标隐私预算之前。特别是动态DP-SGD，特别提高了模型精度，而不会通过逐渐降低剪切值和噪声功率来遵循完全隐私预算约束来牺牲隐私。关于各种深度学习任务的广泛实验，包括图像分类，自然语言处理和联合学习，表明所提出的动态DP-SGD算法稳定更新，因此，在较强烈的隐私保护区中显着提高了模型精度与DP-SGD相比。

虽然在巨大数据上培训的机器学习模型导致了几个领域的断路器，但由于限制数据的访问，他们在隐私敏感域中的部署仍然有限。在私有数据上具有隐私约束的生成模型可以避免此挑战，而是提供对私有数据的间接访问。我们提出DP-Sinkhorn，一种新的最优传输的生成方法，用于从具有差异隐私的私有数据学习数据分布。 DP-Sinkhorn以差别私人方式在模型和数据之间的模型和数据之间最小化陷阱的分歧，将计算上有效的近似值，并在模型和数据之间使用新技术来控制梯度估计的偏差差异的偏差折衷。与现有的培训方法不同，差异私人生成模型主要基于生成的对抗网络，我们不依赖于对抗性目标，这令人惊叹的难以优化，特别是在隐私约束所施加的噪声存在下。因此，DP-Sinkhorn易于训练和部署。通过实验，我们改进了多种图像建模基准的最先进，并显示了差异私有的信息RGB图像综合。项目页面：https：//nv-tlabs.github.io/dp-sinkhorn。

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. This applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in any direction, damaging utility. Metric DP, however, can provide alternative mechanisms based on arbitrary metrics that might be more suitable. In this paper we apply \textit{directional privacy}, via a mechanism based on the von Mises-Fisher (VMF) distribution, to perturb gradients in terms of \textit{angular distance} so that gradient direction is broadly preserved. We show that this provides $\epsilon d$-privacy for deep learning training, rather than the $(\epsilon, \delta)$-privacy of the Gaussian mechanism; and that experimentally, on key datasets, the VMF mechanism can outperform the Gaussian in the utility-privacy trade-off.