已知深度神经网络（DNN）容易受到用不可察觉的扰动制作的对抗性示例的影响，即，输入图像的微小变化会引起错误的分类，从而威胁着基于深度学习的部署系统的可靠性。经常采用对抗训练（AT）来通过训练损坏和干净的数据的混合物来提高DNN的鲁棒性。但是，大多数基于AT的方法在处理\ textit {转移的对抗示例}方面是无效的，这些方法是生成以欺骗各种防御模型的生成的，因此无法满足现实情况下提出的概括要求。此外，对抗性训练一般的国防模型不能对具有扰动的输入产生可解释的预测，而不同的领域专家则需要一个高度可解释的强大模型才能了解DNN的行为。在这项工作中，我们提出了一种基于Jacobian规范和选择性输入梯度正则化（J-SIGR）的方法，该方法通过Jacobian归一化提出了线性化的鲁棒性，还将基于扰动的显着性图正规化，以模仿模型的可解释预测。因此，我们既可以提高DNN的防御能力和高解释性。最后，我们评估了跨不同体系结构的方法，以针对强大的对抗性攻击。实验表明，提出的J-Sigr赋予了针对转移的对抗攻击的鲁棒性，我们还表明，来自神经网络的预测易于解释。

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions themselves can often be fooled by small adversarial perturbations. These problems pose major obstacles for the adoption of neural networks in domains that require security or transparency. In this work, we evaluate the effectiveness of defenses that differentiably penalize the degree to which small changes in inputs can alter model predictions. Across multiple attacks, architectures, defenses, and datasets, we find that neural networks trained with this input gradient regularization exhibit robustness to transferred adversarial examples generated to fool all of the other models. We also find that adversarial examples generated to fool gradient-regularized models fool all other models equally well, and actually lead to more "legitimate," interpretable misclassifications as rated by people (which we confirm in a human subject experiment). Finally, we demonstrate that regularizing input gradients makes them more naturally interpretable as rationales for model predictions. We conclude by discussing this relationship between interpretability and robustness in deep neural networks.

基于深度神经网络（DNN）的智能信息（IOT）系统已被广泛部署在现实世界中。然而，发现DNNS易受对抗性示例的影响，这提高了人们对智能物联网系统的可靠性和安全性的担忧。测试和评估IOT系统的稳健性成为必要和必要。最近已经提出了各种攻击和策略，但效率问题仍未纠正。现有方法是计算地广泛或耗时，这在实践中不适用。在本文中，我们提出了一种称为攻击启发GaN（AI-GaN）的新框架，在有条件地产生对抗性实例。曾经接受过培训，可以有效地给予对抗扰动的输入图像和目标类。我们在白盒设置的不同数据集中应用AI-GaN，黑匣子设置和由最先进的防御保护的目标模型。通过广泛的实验，AI-GaN实现了高攻击成功率，优于现有方法，并显着降低了生成时间。此外，首次，AI-GaN成功地缩放到复杂的数据集。 Cifar-100和Imagenet，所有课程中的成功率约为90美元。

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。

深度神经网络（DNNS）最近在许多分类任务中取得了巨大的成功。不幸的是，它们容易受到对抗性攻击的影响，这些攻击会产生对抗性示例，这些示例具有很小的扰动，以欺骗DNN模型，尤其是在模型共享方案中。事实证明，对抗性训练是最有效的策略，它将对抗性示例注入模型训练中，以提高DNN模型的稳健性，以对对抗性攻击。但是，基于现有的对抗性示例的对抗训练无法很好地推广到标准，不受干扰的测试数据。为了在标准准确性和对抗性鲁棒性之间取得更好的权衡，我们提出了一个新型的对抗训练框架，称为潜在边界引导的对抗训练（梯子），该训练（梯子）在潜在的边界引导的对抗性示例上对对手进行对手训练DNN模型。与大多数在输入空间中生成对抗示例的现有方法相反，梯子通过增加对潜在特征的扰动而产生了无数的高质量对抗示例。扰动是沿SVM构建的具有注意机制的决策边界的正常情况进行的。我们从边界场的角度和可视化视图分析了生成的边界引导的对抗示例的优点。与Vanilla DNN和竞争性底线相比，对MNIST，SVHN，CELEBA和CIFAR-10的广泛实验和详细分析验证了梯子在标准准确性和对抗性鲁棒性之间取得更好的权衡方面的有效性。

评估防御模型的稳健性是对抗对抗鲁棒性研究的具有挑战性的任务。僵化的渐变，先前已经发现了一种梯度掩蔽，以许多防御方法存在并导致鲁棒性的错误信号。在本文中，我们确定了一种更细微的情况，称为不平衡梯度，也可能导致过高的对抗性鲁棒性。当边缘损耗的一个术语的梯度主导并将攻击朝向次优化方向推动时，发生不平衡梯度的现象。为了利用不平衡的梯度，我们制定了分解利润率损失的边缘分解（MD）攻击，并通过两阶段过程分别探讨了这些术语的攻击性。我们还提出了一个Multared和Ensemble版本的MD攻击。通过调查自2018年以来提出的17个防御模型，我们发现6种型号易受不平衡梯度的影响，我们的MD攻击可以减少由最佳基线独立攻击评估的鲁棒性另外2％。我们还提供了对不平衡梯度的可能原因和有效对策的深入分析。

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.

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern on the robustness to adversarial examples, especially for security-critical tasks such as traffic sign identification for autonomous driving. Studies have unveiled the vulnerability of a well-trained DNN by demonstrating the ability of generating barely noticeable (to both human and machines) adversarial images that lead to misclassification. Furthermore, researchers have shown that these adversarial images are highly transferable by simply training and attacking a substitute model built upon the target model, known as a black-box attack to DNNs.Similar to the setting of training substitute models, in this paper we propose an effective black-box attack that also only has access to the input (images) and the output (confidence scores) of a targeted DNN. However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating adversarial examples. We use zeroth order stochastic coordinate descent along with dimension reduction, hierarchical attack and importance sampling techniques to * Pin-Yu Chen and Huan Zhang contribute equally to this work.

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.

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial perturbations are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.

大多数对抗攻击防御方法依赖于混淆渐变。这些方法在捍卫基于梯度的攻击方面是成功的;然而，它们容易被攻击绕过，该攻击不使用梯度或近似近似和使用校正梯度的攻击。不存在不存在诸如对抗培训等梯度的防御，但这些方法通常对诸如其幅度的攻击进行假设。我们提出了一种分类模型，该模型不会混淆梯度，并且通过施工而强大而不承担任何关于攻击的知识。我们的方法将分类作为优化问题，我们“反转”在不受干扰的自然图像上培训的条件发电机，以找到生成最接近查询图像的类。我们假设潜在的脆性抗逆性攻击源是前馈分类器的高度低维性质，其允许对手发现输入空间中的小扰动，从而导致输出空间的大变化。另一方面，生成模型通常是低到高维的映射。虽然该方法与防御GaN相关，但在我们的模型中使用条件生成模型和反演而不是前馈分类是临界差异。与Defense-GaN不同，它被证明生成了容易规避的混淆渐变，我们表明我们的方法不会混淆梯度。我们展示了我们的模型对黑箱攻击的极其强劲，并与自然训练的前馈分类器相比，对白盒攻击的鲁棒性提高。

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.

改善深度神经网络（DNN）对抗对抗示例的鲁棒性是安全深度学习的重要而挑战性问题。跨越现有的防御技术，具有预计梯度体面（PGD）的对抗培训是最有效的。对手训练通过最大化分类丢失，通过最大限度地减少从内在最大化生成的逆势示例的丢失来解决\ excepitient {内部最大化}生成侵略性示例的初始最大优化问题。 。因此，衡量内部最大化的衡量标准是如何对对抗性培训至关重要的。在本文中，我们提出了这种标准，即限制优化（FOSC）的一阶静止条件，以定量评估内部最大化中发现的对抗性实例的收敛质量。通过FOSC，我们发现，为了确保更好的稳健性，必须在培训的\ Texit {稍后的阶段}中具有更好的收敛质量的对抗性示例。然而，在早期阶段，高收敛质量的对抗例子不是必需的，甚至可能导致稳健性差。基于这些观察，我们提出了一种\ Texit {动态}培训策略，逐步提高产生的对抗性实例的收敛质量，这显着提高了对抗性培训的鲁棒性。我们的理论和经验结果表明了该方法的有效性。

深度学习（DL）在许多与人类相关的任务中表现出巨大的成功，这导致其在许多计算机视觉的基础应用中采用，例如安全监控系统，自治车辆和医疗保健。一旦他们拥有能力克服安全关键挑战，这种安全关键型应用程序必须绘制他们的成功部署之路。在这些挑战中，防止或/和检测对抗性实例（AES）。对手可以仔细制作小型，通常是难以察觉的，称为扰动的噪声被添加到清洁图像中以产生AE。 AE的目的是愚弄DL模型，使其成为DL应用的潜在风险。在文献中提出了许多测试时间逃避攻击和对策，即防御或检测方法。此外，还发布了很少的评论和调查，理论上展示了威胁的分类和对策方法，几乎​​没有焦点检测方法。在本文中，我们专注于图像分类任务，并试图为神经网络分类器进行测试时间逃避攻击检测方法的调查。对此类方法的详细讨论提供了在四个数据集的不同场景下的八个最先进的探测器的实验结果。我们还为这一研究方向提供了潜在的挑战和未来的观点。

对抗性培训已被广泛用于增强神经网络模型对抗对抗攻击的鲁棒性。但是，自然准确性与强大的准确性之间仍有一个显着的差距。我们发现其中一个原因是常用的标签，单热量矢量，阻碍了图像识别的学习过程。在本文中，我们提出了一种称为低温蒸馏（LTD）的方法，该方法基于知识蒸馏框架来产生所需的软标记。与以前的工作不同，LTD在教师模型中使用相对较低的温度，采用不同但固定的，温度为教师模型和学生模型。此外，我们已经调查了有限公司协同使用自然数据和对抗性的方法。实验结果表明，在没有额外的未标记数据的情况下，所提出的方法与上一项工作相结合，可以分别在CiFar-10和CiFar-100数据集上实现57.72 \％和30.36 \％的鲁棒精度，这是州的大约1.21 \％通常的方法平均。

由于在量化网络上的按位操作产生的有效存储器消耗和更快的计算，神经网络量化已经变得越来越受欢迎。尽管它们表现出优异的泛化能力，但其鲁棒性属性并不是很好地理解。在这项工作中，我们系统地研究量化网络对基于梯度的对抗性攻击的鲁棒性，并证明这些量化模型遭受梯度消失问题并显示出虚假的鲁棒感。通过归因于培训的网络中的渐变消失到较差的前后信号传播，我们引入了一个简单的温度缩放方法来缓解此问题，同时保留决策边界。尽管对基于梯度的对抗攻击进行了简单的修改，但具有多个网络架构的多个图像分类数据集的实验表明，我们的温度缩放攻击在量化网络上获得了近乎完美的成功率，同时表现出对普遍培训的模型以及浮动的原始攻击以及浮动 - 点网络。代码可在https://github.com/kartikgupta-at-anu/Attack-bnn获得。

The authors thank Nicholas Carlini (UC Berkeley) and Dimitris Tsipras (MIT) for feedback to improve the survey quality. We also acknowledge X. Huang (Uni. Liverpool), K. R. Reddy (IISC), E. Valle (UNICAMP), Y. Yoo (CLAIR) and others for providing pointers to make the survey more comprehensive.

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of deep learning models before they are deployed. However, most of existing adversarial attacks can only fool a black-box model with a low success rate. To address this issue, we propose a broad class of momentum-based iterative algorithms to boost adversarial attacks. By integrating the momentum term into the iterative process for attacks, our methods can stabilize update directions and escape from poor local maxima during the iterations, resulting in more transferable adversarial examples. To further improve the success rates for black-box attacks, we apply momentum iterative algorithms to an ensemble of models, and show that the adversarially trained models with a strong defense ability are also vulnerable to our black-box attacks. We hope that the proposed methods will serve as a benchmark for evaluating the robustness of various deep models and defense methods. With this method, we won the first places in NIPS 2017 Non-targeted Adversarial Attack and Targeted Adversarial Attack competitions.

积极调查深度神经网络的对抗鲁棒性。然而，大多数现有的防御方法限于特定类型的对抗扰动。具体而言，它们通常不能同时为多次攻击类型提供抵抗力，即，它们缺乏多扰动鲁棒性。此外，与图像识别问题相比，视频识别模型的对抗鲁棒性相对未开发。虽然有几项研究提出了如何产生对抗性视频，但在文献中只发表了关于防御策略的少数关于防御策略的方法。在本文中，我们提出了用于视频识别的多种抗逆视频的第一战略之一。所提出的方法称为Multibn，使用具有基于学习的BN选择模块的多个独立批量归一化（BN）层对多个对冲视频类型进行对抗性训练。利用多个BN结构，每个BN Brach负责学习单个扰动类型的分布，从而提供更精确的分布估计。这种机制有利于处理多种扰动类型。 BN选择模块检测输入视频的攻击类型，并将其发送到相应的BN分支，使MultiBN全自动并允许端接训练。与目前的对抗训练方法相比，所提出的Multibn对不同甚至不可预见的对抗性视频类型具有更强的多扰动稳健性，从LP界攻击和物理上可实现的攻击范围。在不同的数据集和目标模型上保持真实。此外，我们进行了广泛的分析，以研究多BN结构的性质。

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。