深度神经网络针对对抗性例子的脆弱性已成为将这些模型部署在敏感领域中的重要问题。事实证明，针对这种攻击的明确防御是具有挑战性的，依赖于检测对抗样本的方法只有在攻击者忽略检测机制时才有效。在本文中，我们提出了一种原则性的对抗示例检测方法，该方法可以承受规范受限的白色框攻击。受K类分类问题的启发，我们训练K二进制分类器，其中I-th二进制分类器用于区分I类的清洁数据和其他类的对抗性样本。在测试时，我们首先使用训练有素的分类器获取输入的预测标签（例如k），然后使用k-th二进制分类器来确定输入是否为干净的样本（k类）或对抗的扰动示例（其他类）。我们进一步设计了一种生成方法来通过将每个二进制分类器解释为类别条件数据的无标准密度模型来检测/分类对抗示例。我们提供上述对抗性示例检测/分类方法的全面评估，并证明其竞争性能和引人注目的特性。

Training adversarially robust discriminative (i.e., softmax) classifier has been the dominant approach to robust classification. Building on recent work on adversarial training (AT)-based generative models, we investigate using AT to learn unnormalized class-conditional density models and then performing generative robust classification. Our result shows that, under the condition of similar model capacities, the generative robust classifier achieves comparable performance to a baseline softmax robust classifier when the test data is clean or when the test perturbation is of limited size, and much better performance when the test perturbation size exceeds the training perturbation size. The generative classifier is also able to generate samples or counterfactuals that more closely resemble the training data, suggesting that the generative classifier can better capture the class-conditional distributions. In contrast to standard discriminative adversarial training where advanced data augmentation techniques are only effective when combined with weight averaging, we find it straightforward to apply advanced data augmentation to achieve better robustness in our approach. Our result suggests that the generative classifier is a competitive alternative to robust classification, especially for problems with limited number of classes.

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.

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。

随着在图像识别中的快速进步和深度学习模型的使用，安全成为他们在安全关键系统中部署的主要关注点。由于深度学习模型的准确性和稳健性主要归因于训练样本的纯度，因此深度学习架构通常易于对抗性攻击。通过对正常图像进行微妙的扰动来获得对抗性攻击，这主要是人类，但可以严重混淆最先进的机器学习模型。什么特别的智能扰动或噪声在正常图像上添加了它导致深神经网络的灾难性分类？使用统计假设检测，我们发现条件变形自身偏析器（CVAE）令人惊讶地擅长检测难以察觉的图像扰动。在本文中，我们展示了CVAE如何有效地用于检测对图像分类网络的对抗攻击。我们展示了我们的成果，Cifar-10数据集，并展示了我们的方法如何为先前的方法提供可比性，以检测对手，同时不会与嘈杂的图像混淆，其中大多数现有方法都摇摇欲坠。

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。

检测分配（OOD）输入对于安全部署现实世界的深度学习模型至关重要。在评估良性分布和OOD样品时，检测OOD示例的现有方法很好。然而，在本文中，我们表明，当在分发的分布和OOD输入时，现有的检测机制可以极其脆弱，其具有最小的对抗扰动，这不会改变其语义。正式地，我们广泛地研究了对共同的检测方法的强大分布检测问题，并表明最先进的OOD探测器可以通过对分布和ood投入增加小扰动来容易地欺骗。为了抵消这些威胁，我们提出了一种称为芦荟的有效算法，它通过将模型暴露于对抗性inlier和异常值示例来执行鲁棒训练。我们的方法可以灵活地结合使用，并使现有方法稳健。在共同的基准数据集上，我们表明芦荟大大提高了最新的ood检测的稳健性，对CiFar-10和46.59％的CiFar-100改善了58.4％的Auroc改善。

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose in this paper a new white-box adversarial attack wrt the l p -norms for p ∈ {1, 2, ∞} aiming at finding the minimal perturbation necessary to change the class of a given input. It has an intuitive geometric meaning, yields quickly high quality results, minimizes the size of the perturbation (so that it returns the robust accuracy at every threshold with a single run). It performs better or similar to stateof-the-art attacks which are partially specialized to one l p -norm, and is robust to the phenomenon of gradient masking.

在过去的几年中，对抗性示例的检测一直是一个热门话题，因为它对于在关键应用程序中安全部署机器学习算法的重要性。但是，通常通过假设一个隐式已知的攻击策略来验证检测方法，这不一定要考虑现实生活中的威胁。确实，这可能导致对检测器性能的过度评估，并可能在竞争检测方案之间的比较中引起一些偏见。我们提出了一个新型的多武器框架，称为Mead，用于根据几种攻击策略来评估探测器，以克服这一限制。其中，我们利用三个新目标来产生攻击。所提出的性能指标基于最坏的情况：仅当正确识别所有不同攻击时，检测才成功。从经验上讲，我们展示了方法的有效性。此外，最先进的探测器获得的表现不佳，为一项新的令人兴奋的研究开放。

Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale problems like ImageNet. We present an algorithm that eliminates the overhead cost of generating adversarial examples by recycling the gradient information computed when updating model parameters.Our "free" adversarial training algorithm achieves comparable robustness to PGD adversarial training on the CIFAR-10 and CIFAR-100 datasets at negligible additional cost compared to natural training, and can be 7 to 30 times faster than other strong adversarial training methods. Using a single workstation with 4 P100 GPUs and 2 days of runtime, we can train a robust model for the large-scale ImageNet classification task that maintains 40% accuracy against PGD attacks. The code is available at https://github.com/ashafahi/free_adv_train.

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

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。

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.

基于深度神经网络的医学图像系统容易受到对抗的例子。在文献中提出了许多防御机制，然而，现有的防御者假设被动攻击者对防御系统知之甚少，并没有根据防御改变攻击战略。最近的作品表明，一个强大的自适应攻击，攻击者被认为具有完全了解防御系统的知识，可以轻松绕过现有的防御。在本文中，我们提出了一种名为Medical Aegis的新型对抗性示例防御系统。据我们所知，医疗AEGIS是文献中的第一次防范，成功地解决了对医学图像的强烈适应性的对抗性示例攻击。医疗AEGIS拥有两层保护剂：第一层垫通过去除其高频分量而削弱了攻击的对抗性操纵能力，但对原始图像的分类性能构成了最小的影响;第二层盾牌学习一组每级DNN模型来预测受保护模型的登录。偏离屏蔽的预测表明对抗性示例。盾牌受到在我们的压力测试中的观察中的观察，即在DNN模型的浅层中存在坚固的小径，自适应攻击难以破坏。实验结果表明，建议的防御精确地检测了自适应攻击，模型推理的开销具有可忽略的开销。

评估对抗性鲁棒性的量，以找到有输入样品被错误分类所需的最小扰动。底层优化的固有复杂性需要仔细调整基于梯度的攻击，初始化，并且可能为许多计算苛刻的迭代而被执行，即使专门用于给定的扰动模型也是如此。在这项工作中，我们通过提出使用不同$ \ ell_p $ -norm扰动模型（$ p = 0，1,2，\ idty $）的快速最小规范（FMN）攻击来克服这些限制（FMN）攻击选择，不需要对抗性起点，并在很少的轻量级步骤中收敛。它通过迭代地发现在$ \ ell_p $ -norm的最大信心被错误分类的样本进行了尺寸的尺寸$ \ epsilon $的限制，同时适应$ \ epsilon $，以最小化当前样本到决策边界的距离。广泛的实验表明，FMN在收敛速度和计算时间方面显着优于现有的攻击，同时报告可比或甚至更小的扰动尺寸。

We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning the theory underlying this trade-off. In this work, we decompose the prediction error for adversarial examples (robust error) as the sum of the natural (classification) error and boundary error, and provide a differentiable upper bound using the theory of classification-calibrated loss, which is shown to be the tightest possible upper bound uniform over all probability distributions and measurable predictors. Inspired by our theoretical analysis, we also design a new defense method, TRADES, to trade adversarial robustness off against accuracy. Our proposed algorithm performs well experimentally in real-world datasets. The methodology is the foundation of our entry to the NeurIPS 2018 Adversarial Vision Challenge in which we won the 1st place out of ~2,000 submissions, surpassing the runner-up approach by 11.41% in terms of mean 2 perturbation distance.

深度神经网络（DNN）通常批评易于对抗性攻击。大多数成功的防御策略采用对抗性培训或随机输入转换，通常需要重新调整或微调模型以实现合理的性能。在这项工作中，我们对预先训练的DNN的中间代表的调查导致了一个有趣的发现，指向对抗性攻击的内在鲁棒性。我们发现，我们可以通过统计表征中间层的神经响应来清洁训练样本来学习生成分类器。当聚合时，多种这样的中间层的分类器的预测显示出对抗对抗攻击的意外鲁棒性。具体而言，我们设计了这些生成分类器的集合，该分类器通过BORDA计数的共识来汇集其预测。我们所提出的方法使用清洁培训数据和预先训练的模型的子集，但对网络架构或对抗攻击生成方法不可知。我们显示广泛的实验，以确定我们的防务战略在想象网验证集中实现最先进的性能。

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.

Adversarial attacks pose safety and security concerns to deep learning applications, but their characteristics are under-explored. Yet largely imperceptible, a strong trace could have been left by PGD-like attacks in an adversarial example. Recall that PGD-like attacks trigger the ``local linearity'' of a network, which implies different extents of linearity for benign or adversarial examples. Inspired by this, we construct an Adversarial Response Characteristics (ARC) feature to reflect the model's gradient consistency around the input to indicate the extent of linearity. Under certain conditions, it qualitatively shows a gradually varying pattern from benign example to adversarial example, as the latter leads to Sequel Attack Effect (SAE). To quantitatively evaluate the effectiveness of ARC, we conduct experiments on CIFAR-10 and ImageNet for attack detection and attack type recognition in a challenging setting. The results suggest that SAE is an effective and unique trace of PGD-like attacks reflected through the ARC feature. The ARC feature is intuitive, light-weighted, non-intrusive, and data-undemanding.