Non-negative matrix factorization is a popular unsupervised machine learning algorithm for extracting meaningful features from data which are inherently non-negative. However, such data sets may often contain privacy-sensitive user data, and therefore, we may need to take necessary steps to ensure the privacy of the users while analyzing the data. In this work, we focus on developing a Non-negative matrix factorization algorithm in the privacy-preserving framework. More specifically, we propose a novel privacy-preserving algorithm for non-negative matrix factorisation capable of operating on private data, while achieving results comparable to those of the non-private algorithm. We design the framework such that one has the control to select the degree of privacy grantee based on the utility gap. We show our proposed framework's performance in six real data sets. The experimental results show that our proposed method can achieve very close performance with the non-private algorithm under some parameter regime, while ensuring strict privacy.

使用敏感用户数据调用隐私保护方法，执行低排名矩阵完成。在这项工作中，我们提出了一种新型的噪声添加机制，用于保留差异隐私，其中噪声分布受Huber损失的启发，Huber损失是众所周知的稳定统计数据中众所周知的损失功能。在使用交替的最小二乘方法来解决矩阵完成问题的同时，对现有的差异隐私机制进行了评估。我们还建议使用迭代重新加权的最小二乘算法来完成低级矩阵，并研究合成和真实数据集中不同噪声机制的性能。我们证明所提出的机制实现了{\ epsilon} - 差异性隐私，类似于拉普拉斯机制。此外，经验结果表明，在某些情况下，Huber机制优于Laplacian和Gaussian，否则是可比的。

作为推荐系统的主要协作过滤方法，一位矩阵完成需要用户收集的数据来提供个性化服务。由于阴险的攻击和意外推断，用户数据的发布通常会引起严重的隐私问题。为了解决此问题，差异隐私（DP）已在标准矩阵完成模型中广泛使用。但是，迄今为止，关于如何在一位矩阵完成中应用DP来实现隐私保护的知之甚少。在本文中，我们提出了一个统一的框架，以确保使用DP对单位矩阵完成的强大隐私保证。在我们的框架中，我们开发了与一位矩阵完成的不同阶段相对应的四种不同的私人扰动机制。对于每种机制，我们设计一个隐私性算法，并提供在适当条件下绑定的理论恢复误差。关于合成和现实世界数据集的数值实验证明了我们的建议的有效性。与没有隐私保护的一位矩阵完成相比，我们提出的机制可以维持高级隐私保护，而边际丧失完成精度。

Conventional matrix factorization relies on centralized collection of users' data for recommendation, which might introduce an increased risk of privacy leakage especially when the recommender is untrusted. Existing differentially private matrix factorization methods either assume the recommender is trusted, or can only provide a uniform level of privacy protection for all users and items with untrusted recommender. In this paper, we propose a novel Heterogeneous Differentially Private Matrix Factorization algorithm (denoted as HDPMF) for untrusted recommender. To the best of our knowledge, we are the first to achieve heterogeneous differential privacy for decentralized matrix factorization in untrusted recommender scenario. Specifically, our framework uses modified stretching mechanism with an innovative rescaling scheme to achieve better trade off between privacy and accuracy. Meanwhile, by allocating privacy budget properly, we can capture homogeneous privacy preference within a user/item but heterogeneous privacy preference across different users/items. Theoretical analysis confirms that HDPMF renders rigorous privacy guarantee, and exhaustive experiments demonstrate its superiority especially in strong privacy guarantee, high dimension model and sparse dataset scenario.

联合学习是一种协作机器学习，参与客户在本地处理他们的数据，仅与协作模型共享更新。这使得能够建立隐私意识的分布式机器学习模型等。目的是通过最大程度地减少一组客户本地存储的数据集的成本函数来优化统计模型的参数。这个过程使客户遇到了两个问题：私人信息的泄漏和模型的个性化缺乏。另一方面，随着分析数据的最新进步，人们对侵犯参与客户的隐私行为的关注激增。为了减轻这种情况，差异隐私及其变体是提供正式隐私保证的标准。客户通常代表非常异构的社区，并拥有非常多样化的数据。因此，与FL社区的最新重点保持一致，以为代表其多样性的用户建立个性化模型框架，这对于防止潜在威胁免受客户的敏感和个人信息而言也是至关重要的。 $ d $ - 私人是对地理位置可区分性的概括，即最近普及的位置隐私范式，它使用了一种基于公制的混淆技术，可保留原始数据的空间分布。为了解决保护客户隐私并允许个性化模型培训以增强系统的公平性和实用性的问题，我们提出了一种提供团体隐私性的方法在FL的框架下。我们为对现实世界数据集的适用性和实验验证提供了理论上的理由，以说明该方法的工作。

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ǫ-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance.

在许多应用程序中，多方拥有有关相同用户的私人数据，但在属性的脱节集上，服务器希望利用数据来训练模型。为了在保护数据主体的隐私时启用模型学习，我们需要垂直联合学习（VFL）技术，其中数据派对仅共享用于培训模型的信息，而不是私人数据。但是，确保共享信息在学习准确的模型的同时保持隐私是一项挑战。据我们所知，本文提出的算法是第一个实用的解决方案，用于差异化垂直联合K-均值聚类，服务器可以在其中获得具有可证明的差异隐私保证的全球中心。我们的算法假设一个不受信任的中央服务器，该服务器汇总了本地数据派对的差异私有本地中心和成员资格编码。它基于收到的信息构建加权网格作为全局数据集的概要。最终中心是通过在加权网格上运行任何K-均值算法而产生的。我们的网格重量估计方法采用了基于Flajolet-Martin草图的新颖，轻巧和差异私有的相交基数估计算法。为了提高两个以上数据方的设置中的估计准确性，我们进一步提出了权重估计算法的精致版本和参数调整策略，以减少最终的K-均值实用程序，以便在中央私人环境中接近它。我们为由我们的算法计算的群集中心提供了理论实用性分析和实验评估结果，并表明我们的方法在理论上和经验上都比基于现有技术的两个基准在理论上和经验上的表现更好。

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, , about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of in order to get acceptable utility of the model, with little understanding of the impact of such choices on meaningful privacy. Moreover, in scenarios where iterative learning procedures are used, differential privacy variants that offer tighter analyses are used which appear to reduce the needed privacy budget but present poorly understood trade-offs between privacy and utility. In this paper, we quantify the impact of these choices on privacy in experiments with logistic regression and neural network models. Our main finding is that there is a huge gap between the upper bounds on privacy loss that can be guaranteed, even with advanced mechanisms, and the effective privacy loss that can be measured using current inference attacks. Current mechanisms for differentially private machine learning rarely offer acceptable utility-privacy trade-offs with guarantees for complex learning tasks: settings that provide limited accuracy loss provide meaningless privacy guarantees, and settings that provide strong privacy guarantees result in useless models.

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.

蜂窝提供商和数据聚合公司从用户设备中占群体的Celluar信号强度测量以生成信号映射，可用于提高网络性能。认识到这种数据收集可能与越来越多的隐私问题的认识可能存在赔率，我们考虑在数据离开移动设备之前混淆这些数据。目标是提高隐私，使得难以从混淆的数据（例如用户ID和用户行踪）中恢复敏感功能，同时仍然允许网络提供商使用用于改进网络服务的数据（即创建准确的信号映射）。要检查本隐私实用程序权衡，我们识别适用于信号强度测量的隐私和公用事业度量和威胁模型。然后，我们使用几种卓越的技术，跨越差异隐私，生成的对抗性隐私和信息隐私技术进行了衡量测量，以便基准，以基准获得各种有前景的混淆方法，并为真实世界的工程师提供指导，这些工程师是负责构建信号映射的现实工程师在不伤害效用的情况下保护隐私。我们的评估结果基于多个不同的现实世界信号映射数据集，展示了同时实现了充足的隐私和实用程序的可行性，并使用了使用该结构和预期使用数据集的策略以及目标平均案例的策略，而不是最坏的情况，保证。

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。

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.

使用机器学习算法从未标记的文本中提取知识可能很复杂。文档分类和信息检索是两个应用程序，可以从无监督的学习（例如文本聚类和主题建模）中受益，包括探索性数据分析。但是，无监督的学习范式提出了可重复性问题。初始化可能会导致可变性，具体取决于机器学习算法。此外，关于群集几何形状，扭曲可能会产生误导。在原因中，异常值和异常的存在可能是决定因素。尽管初始化和异常问题与文本群集和主题建模相关，但作者并未找到对它们的深入分析。这项调查提供了这些亚地区的系统文献综述（2011-2022），并提出了共同的术语，因为类似的程序具有不同的术语。作者描述了研究机会，趋势和开放问题。附录总结了与审查的作品直接或间接相关的文本矢量化，分解和聚类算法的理论背景。

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。

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。

在共享数据的统计学习和分析中，在联合学习和元学习等平台上越来越广泛地采用，有两个主要问题：隐私和鲁棒性。每个参与的个人都应该能够贡献，而不会担心泄露一个人的敏感信息。与此同时，系统应该在恶意参与者的存在中插入损坏的数据。最近的算法在学习中，学习共享数据专注于这些威胁中的一个，使系统容易受到另一个威胁。我们弥合了这个差距，以获得估计意思的规范问题。样品。我们介绍了素数，这是第一算法，实现了各种分布的隐私和鲁棒性。我们通过新颖的指数时间算法进一步补充了这一结果，提高了素数的样本复杂性，实现了近最优保证并匹配（非鲁棒）私有平均估计的已知下限。这证明没有额外的统计成本同时保证隐私和稳健性。

The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In this case, a concrete bound on the error is very relevant to reduce the privacy parameter. The standard mechanism for continual counting is the binary mechanism. We present a novel mechanism and show that its mean squared error is both asymptotically optimal and a factor 10 smaller than the error of the binary mechanism. We also show that the constants in our analysis are almost tight by giving non-asymptotic lower and upper bounds that differ only in the constants of lower-order terms. Our algorithm is a matrix mechanism for the counting matrix and takes constant time per release. We also use our explicit factorization of the counting matrix to give an upper bound on the excess risk of the private learning algorithm of Denisov et al. (NeurIPS 2022). Our lower bound for any continual counting mechanism is the first tight lower bound on continual counting under approximate differential privacy. It is achieved using a new lower bound on a certain factorization norm, denoted by $\gamma_F(\cdot)$, in terms of the singular values of the matrix. In particular, we show that for any complex matrix, $A \in \mathbb{C}^{m \times n}$, \[ \gamma_F(A) \geq \frac{1}{\sqrt{m}}\|A\|_1, \] where $\|\cdot \|$ denotes the Schatten-1 norm. We believe this technique will be useful in proving lower bounds for a larger class of linear queries. To illustrate the power of this technique, we show the first lower bound on the mean squared error for answering parity queries.

在最新的应用中，我们需要在自适应流中进行差异隐私，我们研究了在这种情况下矩阵机制的最佳实例化问题。我们证明了矩阵因素化对自适应流的适用性的基本理论结果，并提供了用于计算最佳因素化的无参数固定点算法。我们就机器学习中自然出现的混凝土矩阵实例化了该框架，并通过用户级别的差异私密性来培训用户级别的差异私有模型，从而在联邦学习中产生了显着的问题。

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep networks on user-partitioned data and privacy accounting for stochastic gradient descent. In particular, we add user-level privacy protection to the federated averaging algorithm, which makes "large step" updates from user-level data. Our work demonstrates that given a dataset with a sufficiently large number of users (a requirement easily met by even small internet-scale datasets), achieving differential privacy comes at the cost of increased computation, rather than in decreased utility as in most prior work. We find that our private LSTM language models are quantitatively and qualitatively similar to un-noised models when trained on a large dataset.

在本文中，我们研究了差异化的私人经验风险最小化（DP-erm）。已经表明，随着尺寸的增加，DP-MER的（最坏的）效用会减小。这是私下学习大型机器学习模型的主要障碍。在高维度中，某些模型的参数通常比其他参数更多的信息是常见的。为了利用这一点，我们提出了一个差异化的私有贪婪坐标下降（DP-GCD）算法。在每次迭代中，DP-GCD私人沿梯度（大约）最大条目执行坐标梯度步骤。从理论上讲，DP-GCD可以通过利用问题解决方案的结构特性（例如稀疏性或准方面的）来改善实用性，并在早期迭代中取得非常快速的进展。然后，我们在合成数据集和真实数据集上以数值说明。最后，我们描述了未来工作的有前途的方向。