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。

机器学习的最新进展主要受益于大规模的可访问培训数据。但是，大规模的数据共享提出了极大的隐私问题。在这项工作中，我们提出了一种基于PAINE框架（G-PATE）的新型隐私保留数据生成模型，旨在训练可缩放的差异私有数据生成器，其保留高生成的数据实用程序。我们的方法利用生成的对抗性网来产生数据，与不同鉴别者之间的私人聚集相结合，以确保强烈的隐私保障。与现有方法相比，G-PATE显着提高了隐私预算的使用。特别是，我们用教师鉴别者的集合训练学生数据发生器，并提出一种新颖的私人梯度聚合机制，以确保对从教师鉴别者流到学生发电机的所有信息的差异隐私。另外，通过随机投影和梯度离散化，所提出的梯度聚合机制能够有效地处理高维梯度向量。从理论上讲，我们证明了G-PATE确保了数据发生器的差异隐私。经验上，我们通过广泛的实验证明了G-PAIN的优越性。我们展示了G-PATE是第一个能够在限量隐私预算下产生高数据实用程序的高维图像数据（$ \ epsilon \ LE 1 $）。我们的代码可在https://github.com/ai-secure/gate上获得。

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。

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.

现代机器学习系统在大型数据集中培训时取得了巨大的成功。但是，这些数据集通常包含敏感信息（例如医疗记录，面部图像），导致严重的隐私问题。差异化私有生成模型（DPGM）通过生成私有化的敏感数据来避免此类隐私问题的解决方案。与其他差异私人（DP）学习者类似，DPGM的主要挑战也是如何在效用和隐私之间取得微妙的平衡。我们提出了DP $^2 $ -VAE，这是一种具有可证明的DP保证的变性自动编码器（VAE）的新型培训机制，并通过\ emph {pre-emph {pre-emph {prec-emph {pret-emph {pret-training}。在相同的DP约束下，DP $^2 $ -VAE最大程度地减少了训练过程中的扰动噪声，从而改善了实用性。 DP $^2 $ -VAE非常灵活，并且对许多其他VAE变体都很容易适应。从理论上讲，我们研究了预训练对私人数据的影响。从经验上讲，我们在图像数据集上进行了广泛的实验，以说明我们在各种隐私预算和评估指标下对基准的优越性。

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.

Differentially private data generation techniques have become a promising solution to the data privacy challenge -- it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in sensitive domains. Unfortunately, restricted by the inherent complexity of modeling high-dimensional distributions, existing private generative models are struggling with the utility of synthetic samples. In contrast to existing works that aim at fitting the complete data distribution, we directly optimize for a small set of samples that are representative of the distribution under the supervision of discriminative information from downstream tasks, which is generally an easier task and more suitable for private training. Our work provides an alternative view for differentially private generation of high-dimensional data and introduces a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.

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.

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。

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。

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at the cost of the resulting ML models' utility. One reason for this is that DP uses one uniform privacy budget epsilon for all training data points, which has to align with the strictest privacy requirement encountered among all data holders. In practice, different data holders have different privacy requirements and data points of data holders with lower requirements can contribute more information to the training process of the ML models. To account for this need, we propose two novel methods based on the Private Aggregation of Teacher Ensembles (PATE) framework to support the training of ML models with individualized privacy guarantees. We formally describe the methods, provide a theoretical analysis of their privacy bounds, and experimentally evaluate their effect on the final model's utility using the MNIST, SVHN, and Adult income datasets. Our empirical results show that the individualized privacy methods yield ML models of higher accuracy than the non-individualized baseline. Thereby, we improve the privacy-utility trade-off in scenarios in which different data holders consent to contribute their sensitive data at different individual privacy levels.

Distributing machine learning predictors enables the collection of large-scale datasets while leaving sensitive raw data at trustworthy sites. We show that locally training support vector machines (SVMs) and computing their averages leads to a learning technique that is scalable to a large number of users, satisfies differential privacy, and is applicable to non-trivial tasks, such as CIFAR-10. For a large number of participants, communication cost is one of the main challenges. We achieve a low communication cost by requiring only a single invocation of an efficient secure multiparty summation protocol. By relying on state-of-the-art feature extractors (SimCLR), we are able to utilize differentially private convex learners for non-trivial tasks such as CIFAR-10. Our experimental results illustrate that for $1{,}000$ users with $50$ data points each, our scheme outperforms state-of-the-art scalable distributed learning methods (differentially private federated learning, short DP-FL) while requiring around $500$ times fewer communication costs: For CIFAR-10, we achieve a classification accuracy of $79.7\,\%$ for an $\varepsilon = 0.59$ while DP-FL achieves $57.6\,\%$. More generally, we prove learnability properties for the average of such locally trained models: convergence and uniform stability. By only requiring strongly convex, smooth, and Lipschitz-continuous objective functions, locally trained via stochastic gradient descent (SGD), we achieve a strong utility-privacy tradeoff.

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。

隐私和沟通效率是联邦神经网络培训中的重要挑战，并将它们组合仍然是一个公开的问题。在这项工作中，我们开发了一种统一高度压缩通信和差异隐私（DP）的方法。我们引入基于相对熵编码（REC）到联合设置的压缩技术。通过对REC进行微小的修改，我们获得了一种可怕的私立学习算法，DP-REC，并展示了如何计算其隐私保证。我们的实验表明，DP-REC大大降低了通信成本，同时提供与最先进的隐私保证。

联合学习（FL）提供了一个有效的范式，可以共同培训分布式用户的数据的全球模型。由于本地培训数据来自可能不值得信赖的不同用户，因此一些研究表明，FL容易受到中毒攻击的影响。同时，为了保护本地用户的隐私，FL始终以差异性私人方式（DPFL）进行培训。因此，在本文中，我们问：我们是否可以利用DPFL的先天隐私权来提供对中毒攻击的认证鲁棒性？我们可以进一步改善FL的隐私以改善这种认证吗？我们首先研究了FL的用户级和实例级别的隐私，并提出了新的机制以获得改进的实例级隐私。然后，我们提供两个鲁棒性认证标准：两级DPFL的认证预测和认证攻击成本。从理论上讲，我们证明了DPFL在有限数量的对抗用户或实例下的认证鲁棒性。从经验上讲，我们进行了广泛的实验，以在对不同数据集的一系列攻击下验证我们的理论。我们表明，具有更严格的隐私保证的DPFL总是在认证攻击成本方面提供更强的鲁棒性认证，但是在隐私保护和公用事业损失之间的适当平衡下，获得了最佳认证预测。

自适应优化方法已成为许多机器学习任务的默认求解器。不幸的是，适应性的好处可能会在具有不同隐私的训练时降低，因为噪声增加了，以确保隐私会降低自适应预处理的有效性。为此，我们提出了ADADP，这是一个使用非敏感的侧面信息来预处梯度的一般框架，从而可以在私有设置中有效使用自适应方法。我们正式显示ADADPS减少了获得类似隐私保证所需的噪声量，从而提高了优化性能。从经验上讲，我们利用简单且随时可用的侧面信息来探索实践中ADADP的性能，与集中式和联合设置中的强大基线相比。我们的结果表明，ADADP平均提高了准确性7.7％（绝对） - 在大规模文本和图像基准上产生最先进的隐私性权衡权衡。

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.

联合学习（FL）是一种从分散数据源训练机器学习模型的技术。我们根据当地的隐私约束概念研究FL，该概念通过在离开客户之前使数据混淆，为敏感数据披露提供了强烈的保护。我们确定了设计实用隐私的FL算法的两个主要问题：沟通效率和高维度的兼容性。然后，我们开发一种基于梯度的学习算法，称为\ emph {sqsgd}（选择性量化的随机梯度下降），以解决这两个问题。所提出的算法基于一种新颖的隐私量化方案，该方案使用每个客户每个维度的恒定位数。然后，我们通过三种方式改进基本算法：首先，我们采用梯度亚采样策略，同时在固定隐私预算下提供更好的培训性能和较小的沟通成本。其次，我们利用随机旋转作为预处理步骤来减少量化误差。第三，采用了自适应梯度标准上限策略来提高准确性和稳定训练。最后，在基准数据集中证明了拟议框架的实用性。实验结果表明，SQSGD成功地学习了Lenet和Resnet等局部隐私约束的大型模型。此外，凭借固定的隐私和通信水平，SQSGD的性能显着主导了各种基线算法。

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.

差异隐私（DP）已被出现为严格的形式主义，以推理可量化的隐私泄漏。在机器学习（ML）中，已采用DP限制推理/披露训练示例。在现有的工作中杠杆横跨ML管道，尽管隔离，通常专注于梯度扰动等机制。在本文中，我们展示了DP-util，DP整体实用分析框架，跨越ML管道，重点是输入扰动，客观扰动，梯度扰动，输出扰动和预测扰动。在隐私敏感数据上给出ML任务，DP-Util使ML隐私从业者能够对DP在这五个扰动点中的影响，以模型公用事业丢失，隐私泄漏和真正透露的数量来测量DP的影响。训练样本。我们在视觉，医疗和金融数据集上使用两个代表性学习算法（Logistic回归和深神经网络）来评估DP-Uts，以防止会员资格推论攻击作为案例研究攻击。我们结果的一个亮点是，预测扰动一致地在所有数据集中始终如一地实现所有模型的最低实用损耗。在Logistic回归模型中，与其他扰动技术相比，客观扰动导致最低的隐私泄漏。对于深度神经网络，梯度扰动导致最低的隐私泄漏。此外，我们的结果揭示了记录的结果表明，由于隐私泄漏增加，差异私有模型揭示了更多数量的成员样本。总体而言，我们的研究结果表明，为了使使用的扰动机制有明智的决定，ML隐私从业者需要检查优化技术（凸与非凸），扰动机制，课程数量和隐私预算之间的动态。