深度神经网络（DNN）已成为实现各种复杂任务的首选技术。但是，正如许多最近的研究所强调的那样，即使是对正确分类的输入的不可察觉的扰动也可能导致DNN错误分类。这使DNNS容易受到攻击者的战略输入操作，并且对环境噪声过敏。为了减轻这种现象，从业人员通过DNNS的“合奏”进行联合分类。通过汇总不同单个DNN的分类输出对相同的输入，基于合奏的分类可以减少因任何单个DNN的随机训练过程的特定实现而导致错误分类的风险。但是，DNN集合的有效性高度依赖于其成员 *在许多不同的输入上没有同时错误 *。在本案例研究中，我们利用DNN验证的最新进展，设计一种方法来识别一种合奏组成，即使输入对对抗性进行了扰动，也不太容易出现同时误差 - 从而导致基于更坚固的集合分类。我们提出的框架使用DNN验证器作为后端，并包括启发式方法，有助于降低直接验证合奏的高复杂性。从更广泛的角度来看，我们的工作提出了一个新颖的普遍目标，以实现正式验证，该目标可能可以改善各种应用领域的现实世界中基于深度学习的系统的鲁棒性。

由于它们在计算机视觉，图像处理和其他人领域的优异性能，卷积神经网络具有极大的普及。不幸的是，现在众所周知，卷积网络通常产生错误的结果 - 例如，这些网络的输入的小扰动可能导致严重的分类错误。近年来提出了许多验证方法，以证明没有此类错误，但这些通常用于完全连接的网络，并且在应用于卷积网络时遭受加剧的可扩展性问题。为了解决这一差距，我们在这里介绍了CNN-ABS框架，特别是旨在验证卷积网络。 CNN-ABS的核心是一种抽象细化技术，它通过拆除卷积连接，以便在这种方式创造原始问题的过度逼近来简化验证问题;如果产生的问题变得过于抽象，它会恢复这些连接。 CNN-ABS旨在使用现有的验证引擎作为后端，我们的评估表明它可以显着提高最先进的DNN验证引擎的性能，平均降低运行时间15.7％。

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.

神经网络在检测嘈杂数据中的模式方面非常成功，并且已成为许多领域的首选技术。但是，他们对对抗攻击的敏感性阻碍了它们的有用性。最近，已经提出了许多用于衡量和改善网络对对抗性扰动的鲁棒性的方法，并且这项不断增长的研究体现了许多明确或隐性的鲁棒性观念。这些概念之间的联系通常是微妙的，文献中缺少它们之间的系统比较。在本文中，我们开始解决这一差距，通过在网络的培训阶段，其验证和部署之后设置对网络鲁棒性作为数学属性的经验分析和评估的一般原则。然后，我们应用这些原则并进行案例研究，以展示我们一般方法的实际好处。

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.

机器学习算法和深度神经网络在几种感知和控制任务中的卓越性能正在推动该行业在安全关键应用中采用这种技术，作为自治机器人和自动驾驶车辆。然而，目前，需要解决几个问题，以使深入学习方法更可靠，可预测，安全，防止对抗性攻击。虽然已经提出了几种方法来提高深度神经网络的可信度，但大多数都是针对特定类的对抗示例量身定制的，因此未能检测到其他角落案件或不安全的输入，这些输入大量偏离训练样本。本文介绍了基于覆盖范式的轻量级监控架构，以增强针对不同不安全输入的模型鲁棒性。特别是，在用于评估多种检测逻辑的架构中提出并测试了四种覆盖分析方法。实验结果表明，该方法有效地检测强大的对抗性示例和分销外输入，引入有限的执行时间和内存要求。

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs. In an application to computer vision, we show that our algorithms can reliably produce samples correctly classified by human subjects but misclassified in specific targets by a DNN with a 97% adversarial success rate while only modifying on average 4.02% of the input features per sample. We then evaluate the vulnerability of different sample classes to adversarial perturbations by defining a hardness measure. Finally, we describe preliminary work outlining defenses against adversarial samples by defining a predictive measure of distance between a benign input and a target classification.

随着深度学习在关键任务系统中的越来越多的应用，越来越需要对神经网络的行为进行正式保证。确实，最近提出了许多用于验证神经网络的方法，但是这些方法通常以有限的可伸缩性或不足的精度而挣扎。许多最先进的验证方案中的关键组成部分是在网络中可以为特定输入域获得的神经元获得的值计算下限和上限 - 并且这些界限更紧密，验证的可能性越大，验证的可能性就越大。成功。计算这些边界的许多常见算法是符号结合传播方法的变化。其中，利用一种称为后替代的过程的方法特别成功。在本文中，我们提出了一种使背部替代产生更严格的界限的方法。为了实现这一目标，我们制定并最大程度地减少背部固定过程中发生的不精确错误。我们的技术是一般的，从某种意义上说，它可以将其集成到许多现有的符号结合的传播技术中，并且只有较小的修改。我们将方法作为概念验证工具实施，并且与执行背部替代的最先进的验证者相比，取得了有利的结果。

神经网络模型已成为各种任务的领先解决方案，例如分类，语言处理，蛋白质折叠等。但是，它们的可靠性受到对抗输入的严重困扰：导致模型产生错误输出的小输入扰动。当系统的环境随机行为，即使在没有恶意的对手的情况下，对抗性输入也可以自然发生，并且在尝试在关键系统中部署神经网络时是严重关注的原因。在本文中，我们提出了一种称为鲁棒性测量和评估（ROMA）的新统计方法，该方法可以衡量神经网络模型的预期鲁棒性。具体而言，罗姆人确定随机输入扰动可能导致错误分类的概率。该方法使我们能够就部署后训练有素的模型会遇到的预期错误的预期频率提供正式的保证。我们的方法可以应用于大规模的黑盒神经网络，与最近提出的验证方法相比，这是一个重要的优势。我们以两种方式运用我们的方法：比较不同模型的鲁棒性，并测量模型的鲁棒性如何受到输入扰动的幅度影响。通过这项工作获得的一个有趣的见解是，在分类网络中，不同的输出标签可以表现出非常不同的鲁棒性水平。我们称这种现象的鲁棒性。我们在分类基础上执行风险和鲁棒性评估的能力为缓解风险打开了大门，这可能是迈向关键安全应用中神经网络认证的重要一步。

在过去的十年中，神经网络（NNS）已被广泛用于许多应用程序，包括安全系统，例如自主系统。尽管采用了新兴的采用，但众所周知，NNS容易受到对抗攻击的影响。因此，提供确保此类系统正常工作的保证非常重要。为了解决这些问题，我们介绍了一个修复不安全NNS W.R.T.的框架。安全规范，即利用可满足的模型理论（SMT）求解器。我们的方法能够通过仅修改其重量值的一些重量值来搜索新的，安全的NN表示形式。此外，我们的技术试图最大程度地提高与原始网络在其决策边界方面的相似性。我们进行了广泛的实验，以证明我们提出的框架能够产生安全NNS W.R.T.的能力。对抗性的鲁棒性特性，只有轻度的准确性损失（就相似性而言）。此外，我们将我们的方法与天真的基线进行比较，以证明其有效性。总而言之，我们提供了一种算法以自动修复具有安全性的算法，并建议一些启发式方法以提高其计算性能。当前，通过遵循这种方法，我们能够产生由分段线性relu激活函数组成的小型（即具有多达数百个参数）的小型（即具有多达数百个参数）。然而，我们的框架是可以合成NNS W.R.T.的一般框架。一阶逻辑规范的任何可决定片段。

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.

The adversarial input generation problem has become central in establishing the robustness and trustworthiness of deep neural nets, especially when they are used in safety-critical application domains such as autonomous vehicles and precision medicine. This is also practically challenging for multiple reasons-scalability is a common issue owing to large-sized networks, and the generated adversarial inputs often lack important qualities such as naturalness and output-impartiality. We relate this problem to the task of patching neural nets, i.e. applying small changes in some of the network$'$s weights so that the modified net satisfies a given property. Intuitively, a patch can be used to produce an adversarial input because the effect of changing the weights can also be brought about by changing the inputs instead. This work presents a novel technique to patch neural networks and an innovative approach of using it to produce perturbations of inputs which are adversarial for the original net. We note that the proposed solution is significantly more effective than the prior state-of-the-art techniques.

We present AI 2 , the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI 2 can automatically prove safety properties (e.g., robustness) of realistic neural networks (e.g., convolutional neural networks).The key insight behind AI 2 is to phrase reasoning about safety and robustness of neural networks in terms of classic abstract interpretation, enabling us to leverage decades of advances in that area. Concretely, we introduce abstract transformers that capture the behavior of fully connected and convolutional neural network layers with rectified linear unit activations (ReLU), as well as max pooling layers. This allows us to handle real-world neural networks, which are often built out of those types of layers.We present a complete implementation of AI 2 together with an extensive evaluation on 20 neural networks. Our results demonstrate that: (i) AI 2 is precise enough to prove useful specifications (e.g., robustness), (ii) AI 2 can be used to certify the effectiveness of state-of-the-art defenses for neural networks, (iii) AI 2 is significantly faster than existing analyzers based on symbolic analysis, which often take hours to verify simple fully connected networks, and (iv) AI 2 can handle deep convolutional networks, which are beyond the reach of existing methods.

背景信息：在过去几年中，机器学习（ML）一直是许多创新的核心。然而，包括在所谓的“安全关键”系统中，例如汽车或航空的系统已经被证明是非常具有挑战性的，因为ML的范式转变为ML带来完全改变传统认证方法。目的：本文旨在阐明与ML为基础的安全关键系统认证有关的挑战，以及文献中提出的解决方案，以解决它们，回答问题的问题如何证明基于机器学习的安全关键系统？'方法：我们开展2015年至2020年至2020年之间发布的研究论文的系统文献综述（SLR），涵盖了与ML系统认证有关的主题。总共确定了217篇论文涵盖了主题，被认为是ML认证的主要支柱：鲁棒性，不确定性，解释性，验证，安全强化学习和直接认证。我们分析了每个子场的主要趋势和问题，并提取了提取的论文的总结。结果：单反结果突出了社区对该主题的热情，以及在数据集和模型类型方面缺乏多样性。它还强调需要进一步发展学术界和行业之间的联系，以加深域名研究。最后，它还说明了必须在上面提到的主要支柱之间建立连接的必要性，这些主要柱主要主要研究。结论：我们强调了目前部署的努力，以实现ML基于ML的软件系统，并讨论了一些未来的研究方向。

尽管机器学习系统的效率和可扩展性，但最近的研究表明，许多分类方法，尤其是深神经网络（DNN），易受对抗的例子;即，仔细制作欺骗训练有素的分类模型的例子，同时无法区分从自然数据到人类。这使得在安全关键区域中应用DNN或相关方法可能不安全。由于这个问题是由Biggio等人确定的。 （2013）和Szegedy等人。（2014年），在这一领域已经完成了很多工作，包括开发攻击方法，以产生对抗的例子和防御技术的构建防范这些例子。本文旨在向统计界介绍这一主题及其最新发展，主要关注对抗性示例的产生和保护。在数值实验中使用的计算代码（在Python和R）公开可用于读者探讨调查的方法。本文希望提交人们将鼓励更多统计学人员在这种重要的令人兴奋的领域的产生和捍卫对抗的例子。

Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify it. With potential applications including perception modules and end-to-end controllers for self-driving cars, this raises concerns about their safety. We develop a novel automated verification framework for feed-forward multi-layer neural networks based on Satisfiability Modulo Theory (SMT). We focus on safety of image classification decisions with respect to image manipulations, such as scratches or changes to camera angle or lighting conditions that would result in the same class being assigned by a human, and define safety for an individual decision in terms of invariance of the classification within a small neighbourhood of the original image. We enable exhaustive search of the region by employing discretisation, and propagate the analysis layer by layer. Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations. If found, adversarial examples can be shown to human testers and/or used to fine-tune the network. We implement the techniques using Z3 and evaluate them on state-of-the-art networks, including regularised and deep learning networks. We also compare against existing techniques to search for adversarial examples and estimate network robustness.

深度神经网络（DNN）的巨大进步导致了各种任务的最先进的性能。然而，最近的研究表明，DNNS容易受到对抗的攻击，这在将这些模型部署到自动驾驶等安全关键型应用时，这使得非常关注。已经提出了不同的防御方法，包括：a）经验防御，通常可以在不提供稳健性认证的情况下再次再次攻击; b）可认真的稳健方法，由稳健性验证组成，提供了在某些条件下的任何攻击和相应的强大培训方法中的稳健准确性的下限。在本文中，我们系统化了可认真的稳健方法和相关的实用和理论意义和调查结果。我们还提供了在不同数据集上现有的稳健验证和培训方法的第一个全面基准。特别是，我们1）为稳健性验证和培训方法提供分类，以及总结代表性算法的方法，2）揭示这些方法中的特征，优势，局限性和基本联系，3）讨论当前的研究进展情况TNN和4的可信稳健方法的理论障碍，主要挑战和未来方向提供了一个开放的统一平台，以评估超过20种代表可认真的稳健方法，用于各种DNN。

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include having malicious content like malware identified as legitimate or controlling vehicle behavior. Yet, all existing adversarial example attacks require knowledge of either the model internals or its training data. We introduce the first practical demonstration of an attacker controlling a remotely hosted DNN with no such knowledge. Indeed, the only capability of our black-box adversary is to observe labels given by the DNN to chosen inputs. Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN. We use the local substitute to craft adversarial examples, and find that they are misclassified by the targeted DNN. To perform a real-world and properly-blinded evaluation, we attack a DNN hosted by MetaMind, an online deep learning API. We find that their DNN misclassifies 84.24% of the adversarial examples crafted with our substitute. We demonstrate the general applicability of our strategy to many ML techniques by conducting the same attack against models hosted by Amazon and Google, using logistic regression substitutes. They yield adversarial examples misclassified by Amazon and Google at rates of 96.19% and 88.94%. We also find that this black-box attack strategy is capable of evading defense strategies previously found to make adversarial example crafting harder.

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

深度学习（DL）系统的安全性是一个极为重要的研究领域，因为它们正在部署在多个应用程序中，因为它们不断改善，以解决具有挑战性的任务。尽管有压倒性的承诺，但深度学习系统容易受到制作的对抗性例子的影响，这可能是人眼无法察觉的，但可能会导致模型错误分类。对基于整体技术的对抗性扰动的保护已被证明很容易受到更强大的对手的影响，或者证明缺乏端到端评估。在本文中，我们试图开发一种新的基于整体的解决方案，该解决方案构建具有不同决策边界的防御者模型相对于原始模型。通过（1）通过一种称为拆分和剃须的方法转换输入的分类器的合奏，以及（2）通过一种称为对比度功能的方法限制重要特征，显示出相对于相对于不同的梯度对抗性攻击，这减少了将对抗性示例从原始示例转移到针对同一类的防御者模型的机会。我们使用标准图像分类数据集（即MNIST，CIFAR-10和CIFAR-100）进行了广泛的实验，以实现最新的对抗攻击，以证明基于合奏的防御的鲁棒性。我们还在存在更强大的对手的情况下评估稳健性，该对手同时靶向合奏中的所有模型。已经提供了整体假阳性和误报的结果，以估计提出的方法的总体性能。