由于对神经网络的运行推断的计算成本，因此通常需要在第三方的计算环境或硬件上部署推论步骤。如果第三方不完全信任，则需要混淆输入和输出的性质，以便第三方无法轻易确定正在执行哪些特定任务。事实证明，存在利用不受信任的政党的协议，但在实践中运行的计算要求太高了。相反，我们探索了一种不同的快速启发式安全策略，我们称之为连接主义符号伪造秘密。通过利用全息降低表示（HRR），我们创建了一个具有伪加密风格的防御的神经网络，从经验上表现出强大的攻击性，即使在不切实际地偏爱对手的威胁模型下也是如此。

全息减少的表示（HRR）是通过将每个向量与抽象概念相关联，并提供数学操作以操纵向量的方法来执行符号AI的方法，以便操纵向量，就像它们是经典的符号对象一样。这种方法在较旧的象征性AI工作和认知科学之外已经很少使用。我们的目标是重新审视这种方法，以了解它是否可行，以使混合神经象征性的方法能够学习作为深度学习架构的可差分量。由于数值不稳定性，HRRS今天在可分辨率的解决方案中无效，我们通过引入迫使向量存在于空间良好的点中的投影步骤来解决问题。这样做，我们将HRRS的概念检索效果提高超过100美元。使用多标签分类，我们演示了如何利用符号HRR属性来开发能够有效学习的输出层和损耗功能，并允许我们调查HRR神经象征性学习方法的一些优缺点。我们的代码可以在https://github.com/neuromorphiccomputationResearchProgram/learning-with-hotographicuredued-representations

在联合学习（FL）中，数据不会在联合培训机器学习模型时留下个人设备。相反，这些设备与中央党（例如，公司）共享梯度。因为数据永远不会“离开”个人设备，因此FL作为隐私保留呈现。然而，最近显示这种保护是一个薄的外观，甚至是一种被动攻击者观察梯度可以重建各个用户的数据。在本文中，我们争辩说，事先工作仍然很大程度上低估了FL的脆弱性。这是因为事先努力专门考虑被动攻击者，这些攻击者是诚实但好奇的。相反，我们介绍了一个活跃和不诚实的攻击者，作为中央会，他们能够在用户计算模型渐变之前修改共享模型的权重。我们称之为修改的重量“陷阱重量”。我们的活跃攻击者能够完全恢复用户数据，并在接近零成本时：攻击不需要复杂的优化目标。相反，它利用了模型梯度的固有数据泄漏，并通过恶意改变共享模型的权重来放大这种效果。这些特异性使我们的攻击能够扩展到具有大型迷你批次数据的模型。如果来自现有工作的攻击者需要小时才能恢复单个数据点，我们的方法需要毫秒来捕获完全连接和卷积的深度神经网络的完整百分之批次数据。最后，我们考虑缓解。我们观察到，FL中的差异隐私（DP）的当前实现是有缺陷的，因为它们明确地信任中央会，并在增加DP噪音的关键任务，因此不提供对恶意中央党的保护。我们还考虑其他防御，并解释为什么它们类似地不足。它需要重新设计FL，为用户提供任何有意义的数据隐私。

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x that is similar to x but classified as t. This makes it difficult to apply neural networks in security-critical areas. Defensive distillation is a recently proposed approach that can take an arbitrary neural network, and increase its robustness, reducing the success rate of current attacks' ability to find adversarial examples from 95% to 0.5%.In this paper, we demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability. Our attacks are tailored to three distance metrics used previously in the literature, and when compared to previous adversarial example generation algorithms, our attacks are often much more effective (and never worse). Furthermore, we propose using high-confidence adversarial examples in a simple transferability test we show can also be used to break defensive distillation. We hope our attacks will be used as a benchmark in future defense attempts to create neural networks that resist adversarial examples.

联合学习允许一组用户在私人训练数据集中培训深度神经网络。在协议期间，数据集永远不会留下各个用户的设备。这是通过要求每个用户向中央服务器发送“仅”模型更新来实现，从而汇总它们以更新深神经网络的参数。然而，已经表明，每个模型更新都具有关于用户数据集的敏感信息（例如，梯度反转攻击）。联合学习的最先进的实现通过利用安全聚合来保护这些模型更新：安全监控协议，用于安全地计算用户的模型更新的聚合。安全聚合是关键，以保护用户的隐私，因为它会阻碍服务器学习用户提供的个人模型更新的源，防止推断和数据归因攻击。在这项工作中，我们表明恶意服务器可以轻松地阐明安全聚合，就像后者未到位一样。我们设计了两种不同的攻击，能够在参与安全聚合的用户数量上，独立于参与安全聚合的用户数。这使得它们在大规模现实世界联邦学习应用中的具体威胁。攻击是通用的，不瞄准任何特定的安全聚合协议。即使安全聚合协议被其理想功能替换为提供完美的安全性的理想功能，它们也同样有效。我们的工作表明，安全聚合与联合学习相结合，当前实施只提供了“虚假的安全感”。

神经网络的外包计算允许用户访问艺术模型的状态，而无需投资专门的硬件和专业知识。问题是用户对潜在的隐私敏感数据失去控制。通过同性恋加密（HE）可以在加密数据上执行计算，而不会显示其内容。在这种知识的系统化中，我们深入了解与隐私保留的神经网络相结合的方法。我们将更改分类为神经网络模型和架构，使其在他和这些变化的影响方面提供影响。我们发现众多挑战是基于隐私保留的深度学习，例如通过加密方案构成的计算开销，可用性和限制。

Machine learning is widely used in practice to produce predictive models for applications such as image processing, speech and text recognition. These models are more accurate when trained on large amount of data collected from different sources. However, the massive data collection raises privacy concerns.In this paper, we present new and efficient protocols for privacy preserving machine learning for linear regression, logistic regression and neural network training using the stochastic gradient descent method. Our protocols fall in the two-server model where data owners distribute their private data among two non-colluding servers who train various models on the joint data using secure two-party computation (2PC). We develop new techniques to support secure arithmetic operations on shared decimal numbers, and propose MPC-friendly alternatives to non-linear functions such as sigmoid and softmax that are superior to prior work. We implement our system in C++. Our experiments validate that our protocols are several orders of magnitude faster than the state of the art implementations for privacy preserving linear and logistic regressions, and scale to millions of data samples with thousands of features. We also implement the first privacy preserving system for training neural networks.

已经提出了安全的多方计算（MPC），以允许多个相互不信任的数据所有者在其合并数据上共同训练机器学习（ML）模型。但是，通过设计，MPC协议忠实地计算了训练功能，对抗性ML社区已证明该功能泄漏了私人信息，并且可以在中毒攻击中篡改。在这项工作中，我们认为在我们的框架中实现的模型合奏是一种称为Safenet的框架，是MPC的高度无限方法，可以避免许多对抗性ML攻击。 MPC培训中所有者之间数据的自然分区允许这种方法在训练时间高度可扩展，可证明可保护免受中毒攻击的保护，并证明可以防御许多隐私攻击。我们展示了Safenet对在端到端和转移学习方案训练的几个机器学习数据集和模型上中毒的效率，准确性和韧性。例如，Safenet可显着降低后门攻击的成功，同时获得$ 39 \ times $ $的培训，$ 36 \ times $ $ $少于达尔斯科夫（Dalskov）等人的四方MPC框架。我们的实验表明，即使在许多非IID设置中，结合也能保留这些好处。结合的简单性，廉价的设置和鲁棒性属性使其成为MPC私下培训ML模型的强大首选。

Federated learning is a collaborative method that aims to preserve data privacy while creating AI models. Current approaches to federated learning tend to rely heavily on secure aggregation protocols to preserve data privacy. However, to some degree, such protocols assume that the entity orchestrating the federated learning process (i.e., the server) is not fully malicious or dishonest. We investigate vulnerabilities to secure aggregation that could arise if the server is fully malicious and attempts to obtain access to private, potentially sensitive data. Furthermore, we provide a method to further defend against such a malicious server, and demonstrate effectiveness against known attacks that reconstruct data in a federated learning setting.

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to normbounded attacks. However these defenses either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired privacy formalism, that provides a rigorous, generic, and flexible foundation for defense.

联合学习使多个用户能够通过共享其模型更新（渐变）来构建联合模型，而其原始数据在其设备上保持本地。与常见的信念相比，这提供了隐私福利，我们在共享渐变时，我们在这里增加了隐私风险的最新结果。具体而言，我们调查梯度（LLG）的标签泄漏，这是一种新建攻击，从他们的共享梯度提取用户培训数据的标签。该攻击利用梯度的方向和幅度来确定任何标签的存在或不存在。 LLG简单且有效，能够泄漏由标签表示的电位敏感信息，并缩放到任意批量尺寸和多个类别。在数学上以及经验上证明了不同设置下攻击的有效性。此外，经验结果表明，LLG在模型训练的早期阶段以高精度成功提取标签。我们还讨论了针对这种泄漏的不同防御机制。我们的研究结果表明，梯度压缩是减轻攻击的实用技术。

Deep Learning has recently become hugely popular in machine learning for its ability to solve end-to-end learning systems, in which the features and the classifiers are learned simultaneously, providing significant improvements in classification accuracy in the presence of highly-structured and large databases.Its success is due to a combination of recent algorithmic breakthroughs, increasingly powerful computers, and access to significant amounts of data.Researchers have also considered privacy implications of deep learning. Models are typically trained in a centralized manner with all the data being processed by the same training algorithm. If the data is a collection of users' private data, including habits, personal pictures, geographical positions, interests, and more, the centralized server will have access to sensitive information that could potentially be mishandled. To tackle this problem, collaborative deep learning models have recently been proposed where parties locally train their deep learning structures and only share a subset of the parameters in the attempt to keep their respective training sets private. Parameters can also be obfuscated via differential privacy (DP) to make information extraction even more challenging, as proposed by Shokri and Shmatikov at CCS'15.Unfortunately, we show that any privacy-preserving collaborative deep learning is susceptible to a powerful attack that we devise in this paper. In particular, we show that a distributed, federated, or decentralized deep learning approach is fundamentally broken and does not protect the training sets of honest participants. The attack we developed exploits the real-time nature of the learning process that allows the adversary to train a Generative Adversarial Network (GAN) that generates prototypical samples of the targeted training set that was meant to be private (the samples generated by the GAN are intended to come from the same distribution as the training data). Interestingly, we show that record-level differential privacy applied to the shared parameters of the model, as suggested in previous work, is ineffective (i.e., record-level DP is not designed to address our attack).

保存隐私的神经网络（NN）推理解决方案最近在几种提供不同的延迟带宽权衡的解决方案方面获得了重大吸引力。其中，许多人依靠同态加密（HE），这是一种对加密数据进行计算的方法。但是，与他们的明文对应物相比，他的操作即使是最先进的计划仍然很慢。修剪NN模型的参数是改善推理潜伏期的众所周知的方法。但是，在明文上下文中有用的修剪方法可能对HE案的改善几乎可以忽略不计，这在最近的工作中也证明了这一点。在这项工作中，我们提出了一套新颖的修剪方法，以减少潜伏期和记忆要求，从而将明文修剪方法的有效性带到HE中。至关重要的是，我们的建议采用两种关键技术，即。堆积模型权重的置换和扩展，使修剪能够明显更多的密封性下文并分别恢复大部分精度损失。我们证明了我们的方法在完全连接的层上的优势，其中使用最近提出的称为瓷砖张量的包装技术填充了权重，该技术允许在非相互作用模式下执行Deep NN推断。我们在各种自动编码器架构上评估了我们的方法，并证明，对于MNIST上的小均值重建损失为1.5*10^{ - 5}，我们将HE-SEAMABLE推断的内存要求和延迟减少了60％。

基于云的机器学习服务（CMLS）使组织能够利用大量数据预先培训的先进模型。然而，使用这些服务的主要缺点是难以保持传输的数据私密和安全。不对称加密需要在云中解密数据，而同性恋加密通常太慢并且难以实现。我们提出了一种通过去卷积（OWSD）的一种方式扰乱（OWSD），一种基于去卷积的加扰框架，其提供了在计算开销的一小部分处的同态加密的优点。当CMLS的输出向量足够大时，对多个图像数据集的广泛评估演示了OWSD实现接近完美分类性能的能力。此外，我们还提供了对我们方法的稳健性的实证分析。

Differentially private federated learning (DP-FL) has received increasing attention to mitigate the privacy risk in federated learning. Although different schemes for DP-FL have been proposed, there is still a utility gap. Employing central Differential Privacy in FL (CDP-FL) can provide a good balance between the privacy and model utility, but requires a trusted server. Using Local Differential Privacy for FL (LDP-FL) does not require a trusted server, but suffers from lousy privacy-utility trade-off. Recently proposed shuffle DP based FL has the potential to bridge the gap between CDP-FL and LDP-FL without a trusted server; however, there is still a utility gap when the number of model parameters is large. In this work, we propose OLIVE, a system that combines the merits from CDP-FL and LDP-FL by leveraging Trusted Execution Environment (TEE). Our main technical contributions are the analysis and countermeasures against the vulnerability of TEE in OLIVE. Firstly, we theoretically analyze the memory access pattern leakage of OLIVE and find that there is a risk for sparsified gradients, which is common in FL. Secondly, we design an inference attack to understand how the memory access pattern could be linked to the training data. Thirdly, we propose oblivious yet efficient algorithms to prevent the memory access pattern leakage in OLIVE. Our experiments on real-world data demonstrate that OLIVE is efficient even when training a model with hundreds of thousands of parameters and effective against side-channel attacks on TEE.

联邦机器学习利用边缘计算来开发网络用户数据的模型，但联合学习的隐私仍然是一个重大挑战。已经提出了使用差异隐私的技术来解决这一点，但是带来了自己的挑战 - 许多人需要一个值得信赖的第三方，或者增加了太多的噪音来生产有用的模型。使用多方计算的\ EMPH {SERVE聚合}的最新进步消除了对第三方的需求，但是在计算上尤其在规模上昂贵。我们提出了一种新的联合学习协议，利用了一种基于与错误学习的技术的新颖差异私有的恶意安全聚合协议。我们的协议优于当前最先进的技术，并且经验结果表明它缩放到大量方面，具有任何差别私有联合学习方案的最佳精度。

拜占庭式联合学习（FL）旨在对抗恶意客户并培训准确的全球模型，同时保持极低的攻击成功率。然而，大多数现有系统仅在诚实/半hon最达克的多数设置中都具有强大的功能。 FLTRUST（NDSS '21）将上下文扩展到对客户的恶意多数，但在训练之前，应在训练之前为服务器提供辅助数据集，以便过滤恶意输入。私人火焰/flguard（Usenix '22）提供了一种解决方案，以确保在半多数上下文中既有稳健性和更新机密性。到目前为止，不可能平衡恶意背景，鲁棒性和更新机密性之间的权衡。为了解决这个问题，我们提出了一种新颖的拜占庭式bybust和隐私的FL系统，称为简介，以捕获恶意的少数群体和多数服务器和客户端。具体而言，基于DBSCAN算法，我们设计了一种通过成对调整的余弦相似性聚类的新方法，以提高聚类结果的准确性。为了阻止多数攻击恶意的攻击，我们开发了一种称为模型分割的算法，在该算法中，同一集群中的本地更新聚集在一起，并且将聚合正确地发送回相应的客户端。我们还利用多种密码工具来执行聚类任务，而无需牺牲培训正确性并更新机密性。我们介绍了详细的安全证明和经验评估以及简要的收敛分析。实验结果表明，简介的测试精度实际上接近FL基线（平均为0.8％的差距）。同时，攻击成功率约为0％-5％。我们进一步优化了设计，以便可以分别降低{67％-89.17％和66.05％-68.75％}的通信开销和运行时。

Neural networks are known to be vulnerable to adversarial examples: inputs that are close to natural inputs but classified incorrectly. In order to better understand the space of adversarial examples, we survey ten recent proposals that are designed for detection and compare their efficacy. We show that all can be defeated by constructing new loss functions. We conclude that adversarial examples are significantly harder to detect than previously appreciated, and the properties believed to be intrinsic to adversarial examples are in fact not. Finally, we propose several simple guidelines for evaluating future proposed defenses.

Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing solutions are either too expensive to be practical or do not sufficiently protect the confidentiality of data and models. In this paper, we study and compare novel \emph{image disguising} mechanisms, DisguisedNets and InstaHide, aiming to achieve a better trade-off among the level of protection for outsourced DNN model training, the expenses, and the utility of data. DisguisedNets are novel combinations of image blocktization, block-level random permutation, and two block-level secure transformations: random multidimensional projection (RMT) and AES pixel-level encryption (AES). InstaHide is an image mixup and random pixel flipping technique \cite{huang20}. We have analyzed and evaluated them under a multi-level threat model. RMT provides a better security guarantee than InstaHide, under the Level-1 adversarial knowledge with well-preserved model quality. In contrast, AES provides a security guarantee under the Level-2 adversarial knowledge, but it may affect model quality more. The unique features of image disguising also help us to protect models from model-targeted attacks. We have done an extensive experimental evaluation to understand how these methods work in different settings for different datasets.

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at ICLR, ICML and NeurIPS-and which illustrate a diverse set of defense strategies-can be circumvented despite attempting to perform evaluations using adaptive attacks. While prior evaluation papers focused mainly on the end result-showing that a defense was ineffective-this paper focuses on laying out the methodology and the approach necessary to perform an adaptive attack. Some of our attack strategies are generalizable, but no single strategy would have been sufficient for all defenses. This underlines our key message that adaptive attacks cannot be automated and always require careful and appropriate tuning to a given defense. We hope that these analyses will serve as guidance on how to properly perform adaptive attacks against defenses to adversarial examples, and thus will allow the community to make further progress in building more robust models.