在过去的十年中，已经对对抗性的例子，旨在诱导机器学习模型中最坏情况行为的输入进行了广泛的研究。然而，我们对这一现象的理解源于相当零散的知识库。目前，有少数攻击，每个攻击在威胁模型中都有不同的假设和无与伦比的最优定义。在本文中，我们提出了一种系统的方法来表征最坏情况（即最佳）对手。我们首先通过将攻击组件雾化到表面和旅行者中，引入对抗机器学习中攻击的扩展分解。通过分解，我们列举了组件以创建576次攻击（以前没有探索568次攻击）。接下来，我们提出了帕累托合奏攻击（PEA）：上限攻击性能的理论攻击。有了我们的新攻击，我们衡量相对于PEA的性能：稳健和非稳定模型，七个数据集和三个扩展的基于LP的威胁模型，其中包含计算成本，从而形式化了对抗性策略的空间。从我们的评估中，我们发现攻击性能是高度背景的：域，稳健性和威胁模型可以对攻击效率产生深远的影响。我们的调查表明，未来衡量机器学习安全性的研究应：（1）与域和威胁模型背景相关，并且（2）超越了当今使用的少数已知攻击。

机器学习容易受到对抗的示例 - 输入，旨在使模型表现不佳。但是，如果对逆势示例代表建模域中的现实输入，则尚不清楚。不同的域，如网络和网络钓鱼具有域制约束 - 在对手必须满足攻击方面必须满足要实现的攻击（除了任何对手特定的目标）之间的特征之间的复杂关系。在本文中，我们探讨了域限制如何限制对抗性能力以及对手如何适应创建现实（符合限制）示例的策略。在此，我们开发从数据学习域约束的技术，并展示如何将学习的约束集成到对抗性制作过程中。我们评估我们在网络入侵和网络钓鱼数据集中的方法的功效，并发现：（1）最多82％的对抗实例由最先进的制作算法产生的违规结构域约束，（2）域约束对对抗性鲁棒例子;强制约束产生模型精度的增加高达34％。我们不仅观察到对手必须改变投入以满足领域约束，但这些约束使得产生有效的对抗例子的产生远远挑战。

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.

机器学习算法已被证明通过系统修改（例如，图像识别）中的输入（例如，对抗性示例）的系统修改（例如，对抗性示例）容易受到对抗操作的影响。在默认威胁模型下，对手利用了图像的无约束性质。每个功能（像素）完全由对手控制。但是，尚不清楚这些攻击如何转化为限制对手可以修改的特征以及如何修改特征的约束域（例如，网络入侵检测）。在本文中，我们探讨了受约束的域是否比不受约束的域对对抗性示例生成算法不那么脆弱。我们创建了一种用于生成对抗草图的算法：针对性的通用扰动向量，该向量在域约束的信封内编码特征显着性。为了评估这些算法的性能，我们在受约束（例如网络入侵检测）和不受约束（例如图像识别）域中评估它们。结果表明，我们的方法在约束域中产生错误分类率，这些域与不受约束的域（大于95％）相当。我们的调查表明，受约束域暴露的狭窄攻击表面仍然足够大，可以制作成功的对抗性例子。因此，约束似乎并不能使域变得健壮。实际上，只有五个随机选择的功能，仍然可以生成对抗性示例。

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.

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.

Designing powerful adversarial attacks is of paramount importance for the evaluation of $\ell_p$-bounded adversarial defenses. Projected Gradient Descent (PGD) is one of the most effective and conceptually simple algorithms to generate such adversaries. The search space of PGD is dictated by the steepest ascent directions of an objective. Despite the plethora of objective function choices, there is no universally superior option and robustness overestimation may arise from ill-suited objective selection. Driven by this observation, we postulate that the combination of different objectives through a simple loss alternating scheme renders PGD more robust towards design choices. We experimentally verify this assertion on a synthetic-data example and by evaluating our proposed method across 25 different $\ell_{\infty}$-robust models and 3 datasets. The performance improvement is consistent, when compared to the single loss counterparts. In the CIFAR-10 dataset, our strongest adversarial attack outperforms all of the white-box components of AutoAttack (AA) ensemble, as well as the most powerful attacks existing on the literature, achieving state-of-the-art results in the computational budget of our study ($T=100$, no restarts).

The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of robustness. Many promising defenses could be broken later on, making it difficult to identify the state-of-the-art. Frequent pitfalls in the evaluation are improper tuning of hyperparameters of the attacks, gradient obfuscation or masking. In this paper we first propose two extensions of the PGD-attack overcoming failures due to suboptimal step size and problems of the objective function. We then combine our novel attacks with two complementary existing ones to form a parameter-free, computationally affordable and user-independent ensemble of attacks to test adversarial robustness. We apply our ensemble to over 50 models from papers published at recent top machine learning and computer vision venues. In all except one of the cases we achieve lower robust test accuracy than reported in these papers, often by more than 10%, identifying several broken defenses.

添加到输入的最小侵犯扰动已被证明在愚弄深度神经网络方面有效。在本文中，我们介绍了几种创新，使白盒子目标攻击遵循攻击者的目标：欺骗模型将更高的目标类概率分配比任何其他更高的概率，同时停留在距原始距离的指定距离内输入。首先，我们提出了一种新的损失函数，明确地捕获了目标攻击的目标，特别是通过使用所有类的Logits而不是仅仅是一个子集。我们表明，具有这种损失功能的自动PGD比与其他常用损耗功能相比发现更多的对抗示例。其次，我们提出了一种新的攻击方法，它使用进一步发发版本的我们的损失函数捕获错误分类目标和$ l _ {\ infty} $距离限制$ \ epsilon $。这种新的攻击方法在CIFAR10 DataSet上比较成功了1.5--4.2％，而在ImageNet DataSet上比下一个最先进的攻击更成功。我们使用统计测试确认，我们的攻击优于最先进的攻击不同数据集和$ \ epsilon $和不同防御的价值。

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate adversarial risk as an objective for achieving models robust to worst-case inputs. We then frame commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarial risk. This suggests that models may optimize this surrogate rather than the true adversarial risk. We formalize this notion as obscurity to an adversary, and develop tools and heuristics for identifying obscured models and designing transparent models. We demonstrate that this is a significant problem in practice by repurposing gradient-free optimization techniques into adversarial attacks, which we use to decrease the accuracy of several recently proposed defenses to near zero. Our hope is that our formulations and results will help researchers to develop more powerful defenses.

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimizationbased attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining noncertified white-box-secure defenses at ICLR 2018, we find obfuscated gradients are a common occurrence, with 7 of 9 defenses relying on obfuscated gradients. Our new attacks successfully circumvent 6 completely, and 1 partially, in the original threat model each paper considers.

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.

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）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。

作为研究界，我们仍然缺乏对对抗性稳健性的进展的系统理解，这通常使得难以识别训练强大模型中最有前途的想法。基准稳健性的关键挑战是，其评估往往是出错的导致鲁棒性高估。我们的目标是建立对抗性稳健性的标准化基准，尽可能准确地反映出考虑在合理的计算预算范围内所考虑的模型的稳健性。为此，我们首先考虑图像分类任务并在允许的型号上引入限制（可能在将来宽松）。我们评估了与AutoAtrack的对抗鲁棒性，白和黑箱攻击的集合，最近在大规模研究中显示，与原始出版物相比，改善了几乎所有稳健性评估。为防止对自动攻击进行新防御的过度适应，我们欢迎基于自适应攻击的外部评估，特别是在自动攻击稳健性潜在高估的地方。我们的排行榜，托管在https://robustbench.github.io/，包含120多个模型的评估，并旨在反映在$ \ ell_ \ infty $的一套明确的任务上的图像分类中的当前状态 - 和$ \ ell_2 $ -Threat模型和共同腐败，未来可能的扩展。此外，我们开源源是图书馆https://github.com/robustbench/robustbench，可以提供对80多个强大模型的统一访问，以方便他们的下游应用程序。最后，根据收集的模型，我们分析了稳健性对分布换档，校准，分配检测，公平性，隐私泄漏，平滑度和可转移性的影响。

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.

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.

许多机器学习问题在表格域中使用数据。对抗性示例可能对这些应用尤其有害。然而，现有关于对抗鲁棒性的作品主要集中在图像和文本域中的机器学习模型。我们认为，由于表格数据和图像或文本之间的差异，现有的威胁模型不适合表格域。这些模型没有捕获该成本比不可识别更重要，也不能使对手可以将不同的价值归因于通过部署不同的对手示例获得的效用。我们表明，由于这些差异，用于图像的攻击和防御方法和文本无法直接应用于表格设置。我们通过提出新的成本和公用事业感知的威胁模型来解决这些问题，该模型量身定制了针对表格域的攻击者的攻击者的约束。我们介绍了一个框架，使我们能够设计攻击和防御机制，从而导致模型免受成本或公用事业意识的对手的影响，例如，受到一定美元预算约束的对手。我们表明，我们的方法在与对应于对抗性示例具有经济和社会影响的应用相对应的三个表格数据集中有效。

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted using fast single-step methods that maximize a linear approximation of the model's loss. We show that this form of adversarial training converges to a degenerate global minimum, wherein small curvature artifacts near the data points obfuscate a linear approximation of the loss. The model thus learns to generate weak perturbations, rather than defend against strong ones. As a result, we find that adversarial training remains vulnerable to black-box attacks, where we transfer perturbations computed on undefended models, as well as to a powerful novel single-step attack that escapes the non-smooth vicinity of the input data via a small random step. We further introduce Ensemble Adversarial Training, a technique that augments training data with perturbations transferred from other models. On ImageNet, Ensemble Adversarial Training yields models with stronger robustness to blackbox attacks. In particular, our most robust model won the first round of the NIPS 2017 competition on Defenses against Adversarial Attacks (Kurakin et al., 2017c). However, subsequent work found that more elaborate black-box attacks could significantly enhance transferability and reduce the accuracy of our 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.