深度神经网络模型大量部署在各种硬件平台上。这导致出现新的攻击向量，这些攻击向量大大扩展了标准攻击表面，这是由对抗机器学习社区广泛研究的。旨在通过瞄准存储在内存中的参数（权重）的第一个旨在极大地降低模型性能的攻击之一是位翼攻击（BFA）。在这项工作中，我们指出了与BFA相关的一些评估挑战。首先，标准威胁模型中缺乏对手的预算是有问题的，尤其是在处理身体攻击时。此外，由于BFA提出了关键的可变性，因此我们讨论了某些培训参数的影响以及模型体系结构的重要性。这项工作是第一个介绍BFA对与卷积神经网络相比呈现不同行为的完全连接体系结构的影响的作品。这些结果突出了定义鲁棒和合理评估方法的重要性，以正确评估基于参数的攻击的危险，并衡量国防提供的实际鲁棒性水平。

Model extraction is a major threat for embedded deep neural network models that leverages an extended attack surface. Indeed, by physically accessing a device, an adversary may exploit side-channel leakages to extract critical information of a model (i.e., its architecture or internal parameters). Different adversarial objectives are possible including a fidelity-based scenario where the architecture and parameters are precisely extracted (model cloning). We focus this work on software implementation of deep neural networks embedded in a high-end 32-bit microcontroller (Cortex-M7) and expose several challenges related to fidelity-based parameters extraction through side-channel analysis, from the basic multiplication operation to the feed-forward connection through the layers. To precisely extract the value of parameters represented in the single-precision floating point IEEE-754 standard, we propose an iterative process that is evaluated with both simulations and traces from a Cortex-M7 target. To our knowledge, this work is the first to target such an high-end 32-bit platform. Importantly, we raise and discuss the remaining challenges for the complete extraction of a deep neural network model, more particularly the critical case of biases.

神经网络权重的对抗性比特翻转攻击（BFA）可以通过翻转非常少量的比特来导致灾难性的精度下降。先前比特翻转攻击技术的主要缺点是他们对测试数据的依赖。包含敏感或专有数据的应用程序通常是不可能的。在本文中，我们提出了盲目数据侵犯比特 - 翻转攻击（BDFA），一种新颖的技术，使BFA能够无任何访问训练或测试数据。这是通过优化合成数据集来实现的，该数据集被设计为匹配跨网络的不同层和目标标签的批量标准化的统计数据。实验结果表明，BDFA可以显着降低75.96 \％至13.94 \％的resnet50的准确性，只有4位翻转。

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by adversarial examples that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, feature squeezing, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives.This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.

普遍的对策扰动是图像不可思议的和模型 - 无关的噪声，当添加到任何图像时可以误导训练的深卷积神经网络进入错误的预测。由于这些普遍的对抗性扰动可以严重危害实践深度学习应用的安全性和完整性，因此现有技术使用额外的神经网络来检测输入图像源的这些噪声的存在。在本文中，我们展示了一种攻击策略，即通过流氓手段激活（例如，恶意软件，木马）可以通过增强AI硬件加速器级的对抗噪声来绕过这些现有对策。我们使用Conv2D功能软件内核的共同仿真和FuseSoC环境下的硬件的Verilog RTL模型的共同仿真，展示了关于几个深度学习模型的加速度普遍对抗噪声。

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.

Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial samples: inputs crafted to force a deep neural network (DNN) to provide adversary-selected outputs. Such attacks can seriously undermine the security of the system supported by the DNN, sometimes with devastating consequences. For example, autonomous vehicles can be crashed, illicit or illegal content can bypass content filters, or biometric authentication systems can be manipulated to allow improper access. In this work, we introduce a defensive mechanism called defensive distillation to reduce the effectiveness of adversarial samples on DNNs. We analytically investigate the generalizability and robustness properties granted by the use of defensive distillation when training DNNs. We also empirically study the effectiveness of our defense mechanisms on two DNNs placed in adversarial settings. The study shows that defensive distillation can reduce effectiveness of sample creation from 95% to less than 0.5% on a studied DNN. Such dramatic gains can be explained by the fact that distillation leads gradients used in adversarial sample creation to be reduced by a factor of 10 30 . We also find that distillation increases the average minimum number of features that need to be modified to create adversarial samples by about 800% on one of the DNNs we tested.

机器学习模型严重易于来自对抗性示例的逃避攻击。通常，对逆势示例的修改输入类似于原始输入的修改输入，在WhiteBox设置下由对手的WhiteBox设置构成，完全访问模型。然而，最近的攻击已经显示出使用BlackBox攻击的对逆势示例的查询号显着减少。特别是，警报是从越来越多的机器学习提供的经过培训的模型的访问界面中利用分类决定作为包括Google，Microsoft，IBM的服务提供商，并由包含这些模型的多种应用程序使用的服务提供商来利用培训的模型。对手仅利用来自模型的预测标签的能力被区别为基于决策的攻击。在我们的研究中，我们首先深入潜入最近的ICLR和SP的最先进的决策攻击，以突出发现低失真对抗采用梯度估计方法的昂贵性质。我们开发了一种强大的查询高效攻击，能够避免在梯度估计方法中看到的嘈杂渐变中的局部最小和误导中的截留。我们提出的攻击方法，ramboattack利用随机块坐标下降的概念来探索隐藏的分类器歧管，针对扰动来操纵局部输入功能以解决梯度估计方法的问题。重要的是，ramboattack对对对手和目标类别可用的不同样本输入更加强大。总的来说，对于给定的目标类，ramboattack被证明在实现给定查询预算的较低失真时更加强大。我们使用大规模的高分辨率ImageNet数据集来策划我们的广泛结果，并在GitHub上开源我们的攻击，测试样本和伪影。

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。

在本文中，我们通过合成自己的攻击数据集来提出基于零数据的重复比特翻转攻击（ZEBRA），精确地破坏了深度神经网络（DNN）。许多先前的对抗性重量攻击的作品不仅需要重量参数，而且需要在搜索易受攻击的比特中进行攻击的训练或测试数据集。我们建议通过利用受害者DNN模型中的批量归一化层统计来综合名为Dizeted目标数据的攻击数据集。配备蒸馏的目标数据，我们的Zebra算法可以在模型中搜索易受攻击的位，而无需访问培训或测试数据集。因此，我们的方法使对抗性重量攻击更致命的DNN的安全性。我们的实验结果表明，与先前的攻击方法相比，平均需要2.0倍（CiFar-10）和1.6倍（想象成）的比特翻转数量少。我们的代码可在https：// github上获得。COM / PDH930105 / ZEBRA。

最近对机器学习（ML）模型的攻击，例如逃避攻击，具有对抗性示例，并通过提取攻击窃取了一些模型，构成了几种安全性和隐私威胁。先前的工作建议使用对抗性训练从对抗性示例中保护模型，以逃避模型的分类并恶化其性能。但是，这种保护技术会影响模型的决策边界及其预测概率，因此可能会增加模型隐私风险。实际上，仅使用对模型预测输出的查询访问的恶意用户可以提取它并获得高智能和高保真替代模型。为了更大的提取，这些攻击利用了受害者模型的预测概率。实际上，所有先前关于提取攻击的工作都没有考虑到出于安全目的的培训过程中的变化。在本文中，我们提出了一个框架，以评估具有视觉数据集对对抗训练的模型的提取攻击。据我们所知，我们的工作是第一个进行此类评估的工作。通过一项广泛的实证研究，我们证明了受对抗训练的模型比在自然训练情况下获得的模型更容易受到提取攻击的影响。他们可以达到高达$ \ times1.2 $更高的准确性和同意，而疑问低于$ \ times0.75 $。我们还发现，与从自然训练的（即标准）模型中提取的DNN相比，从鲁棒模型中提取的对抗性鲁棒性能力可通过提取攻击（即从鲁棒模型提取的深神经网络（DNN）提取的深神网络（DNN））传递。

鉴于对机器学习模型的访问，可以进行对手重建模型的培训数据？这项工作从一个强大的知情对手的镜头研究了这个问题，他们知道除了一个之外的所有培训数据点。通过实例化混凝土攻击，我们表明重建此严格威胁模型中的剩余数据点是可行的。对于凸模型（例如Logistic回归），重建攻击很简单，可以以封闭形式导出。对于更常规的模型（例如神经网络），我们提出了一种基于训练的攻击策略，该攻击策略接收作为输入攻击的模型的权重，并产生目标数据点。我们展示了我们对MNIST和CIFAR-10训练的图像分类器的攻击的有效性，并系统地研究了标准机器学习管道的哪些因素影响重建成功。最后，我们从理论上调查了有多差异的隐私足以通过知情对手减轻重建攻击。我们的工作提供了有效的重建攻击，模型开发人员可以用于评估超出以前作品中考虑的一般设置中的个别点的记忆（例如，生成语言模型或访问培训梯度）;它表明，标准模型具有存储足够信息的能力，以实现培训数据点的高保真重建;它表明，差异隐私可以成功减轻该参数制度中的攻击，其中公用事业劣化最小。

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.

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.

在过去的几十年中，人工智能的兴起使我们有能力解决日常生活中最具挑战性的问题，例如癌症的预测和自主航行。但是，如果不保护对抗性攻击，这些应用程序可能不会可靠。此外，最近的作品表明，某些对抗性示例可以在不同的模型中转移。因此，至关重要的是避免通过抵抗对抗性操纵的强大模型进行这种可传递性。在本文中，我们提出了一种基于特征随机化的方法，该方法抵抗了八次针对测试阶段深度学习模型的对抗性攻击。我们的新方法包括改变目标网络分类器中的训练策略并选择随机特征样本。我们认为攻击者具有有限的知识和半知识条件，以进行最普遍的对抗性攻击。我们使用包括现实和合成攻击的众所周知的UNSW-NB15数据集评估了方法的鲁棒性。之后，我们证明我们的策略优于现有的最新方法，例如最强大的攻击，包括针对特定的对抗性攻击进行微调网络模型。最后，我们的实验结果表明，我们的方法可以确保目标网络并抵抗对抗性攻击的转移性超过60％。

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples-inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides us with a broad and unifying view on much of the prior work on this topic. Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal. In particular, they specify a concrete security guarantee that would protect against any adversary. These methods let us train networks with significantly improved resistance to a wide range of adversarial attacks. They also suggest the notion of security against a first-order adversary as a natural and broad security guarantee. We believe that robustness against such well-defined classes of adversaries is an important stepping stone towards fully resistant deep learning models. 1

深度神经网络（DNN）的最新进步已经看到多个安全敏感域中的广泛部署。需要资源密集型培训和使用有价值的域特定培训数据，使这些模型成为模型所有者的顶级知识产权（IP）。 DNN隐私的主要威胁之一是模型提取攻击，前提是在DNN模型中试图窃取敏感信息。最近的研究表明，基于硬件的侧信道攻击可以揭示关于DNN模型的内部知识（例如，模型架构）但到目前为止，现有攻击不能提取详细的模型参数（例如，权重/偏置）。在这项工作中，我们首次提出了一种先进的模型提取攻击框架，借助记忆侧通道攻击有效地窃取了DNN权重。我们建议的深度包括两个关键阶段。首先，我们通过采用基于Rowhammer的硬件故障技术作为信息泄漏向量，开发一种名为HammerLeak的新重量位信息提取方法。 Hammerleak利用了用于DNN应用的几种新的系统级技术，以实现快速高效的重量窃取。其次，我们提出了一种具有平均聚类重量惩罚的新型替代模型训练算法，其利用部分泄漏的位信息有效地利用了目标受害者模型的替代原型。我们在三个流行的图像数据集（例如，CiFar-10/100 / GTSRB）和四个DNN架构上评估该替代模型提取方法（例如，Reset-18/34 / Wide-Reset / Vgg-11）。提取的替代模型在CiFar-10数据集的深度剩余网络上成功实现了超过90％的测试精度。此外，我们提取的替代模型也可能产生有效的对抗性输入样本来欺骗受害者模型。

We propose the Square Attack, a score-based black-box l2and l∞-adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. Square Attack is based on a randomized search scheme which selects localized squareshaped updates at random positions so that at each iteration the perturbation is situated approximately at the boundary of the feasible set. Our method is significantly more query efficient and achieves a higher success rate compared to the state-of-the-art methods, especially in the untargeted setting. In particular, on ImageNet we improve the average query efficiency in the untargeted setting for various deep networks by a factor of at least 1.8 and up to 3 compared to the recent state-ofthe-art l∞-attack of Al-Dujaili & OReilly (2020). Moreover, although our attack is black-box, it can also outperform gradient-based white-box attacks on the standard benchmarks achieving a new state-of-the-art in terms of the success rate. The code of our attack is available at https://github.com/max-andr/square-attack.

在培训机器学习模型期间，它们可能会存储或“了解”有关培训数据的更多信息，而不是预测或分类任务所需的信息。属性推理攻击旨在从给定模型的培训数据中提取统计属性，而无需访问培训数据本身，从而利用了这一点。这些属性可能包括图片的质量，以识别相机模型，以揭示产品的目标受众的年龄分布或在计算机网络中使用恶意软件攻击的随附的主机类型。当攻击者可以访问所有模型参数时，即在白色盒子方案中，此攻击尤其准确。通过捍卫此类攻击，模型所有者可以确保其培训数据，相关的属性以及其知识产权保持私密，即使他们故意共享自己的模型，例如协作培训或模型泄漏。在本文中，我们介绍了属性，这是针对白盒属性推理攻击的有效防御机制，独立于培训数据类型，模型任务或属性数量。属性通过系统地更改目标模型的训练的权重和偏见来减轻属性推理攻击，从而使对手无法提取所选属性。我们在三个不同的数据集（包括表格数据和图像数据）以及两种类型的人工神经网络（包括人造神经网络）上进行了经验评估属性。我们的研究结果表明，以良好的隐私性权衡取舍，可以保护机器学习模型免受财产推理攻击的侵害，既有效又可靠。此外，我们的方法表明该机制也有效地取消了多个特性。

有必要提高某些特殊班级的表现，或者特别保护它们免受对抗学习的攻击。本文提出了一个将成本敏感分类和对抗性学习结合在一起的框架，以训练可以区分受保护和未受保护的类的模型，以使受保护的类别不太容易受到对抗性示例的影响。在此框架中，我们发现在训练深神经网络（称为Min-Max属性）期间，一个有趣的现象，即卷积层中大多数参数的绝对值。基于这种最小的最大属性，该属性是在随机分布的角度制定和分析的，我们进一步建立了一个针对对抗性示例的新防御模型，以改善对抗性鲁棒性。构建模型的一个优点是，它的性能比标准模型更好，并且可以与对抗性训练相结合，以提高性能。在实验上证实，对于所有类别的平均准确性，我们的模型在没有发生攻击时几乎与现有模型一样，并且在发生攻击时比现有模型更好。具体而言，关于受保护类的准确性，提议的模型比发生攻击时的现有模型要好得多。