使分类器对对抗性示例的强大实例很难。因此，许多防御能够应对检测扰动输入的看似更容易的任务。我们对这个目标显示了一个障碍。我们证明了对抗性示例的检测和分类之间的一般硬度降低：给定对距离处攻击的强大检测器{\ epsilon}（在某些度量中），我们可以在距离处构建类似强大的（但效率低下）的分类器，以{}/2。我们的减少在计算上效率低下，因此不能用于构建实用分类器。取而代之的是，测试经验检测是否意味着比作者可能预期的要强得多，这是一种有用的理智检查。为了说明，我们重新访问13个检测器防御。对于11/13的案例，我们表明所要求的检测结果将意味着效率低下的分类器稳健性远远超出了最先进的情况。

已经提出了数百种防御能力，以使深度神经网络可靠，以防止最小的（对抗）输入扰动。但是，只有少数这些防御能力提高了他们的主张，因为正确评估鲁棒性是极具挑战性的：弱攻击即使在不知不觉中也无法找到对抗性示例，从而使脆弱的网络看起来很健壮。在本文中，我们提出了一项测试，以识别弱攻击，从而确定弱国防评估。我们的测试稍微修改了神经网络，以确保每个样本的对抗示例存在。因此，任何正确的攻击都必须成功打破此修改后的网络。在13个先前出版的防御措施中，有11个对防御的最初评估未能通过我们的测试，而打破这些防御的更强烈的攻击则使它通过了。我们希望攻击单元测试（例如我们的）将成为未来鲁棒性评估的主要组成部分，并增加对当前受到怀疑的经验领域的信心。

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.

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.

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.

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。

在测试时间进行优化的自适应防御能力有望改善对抗性鲁棒性。我们对这种自适应测试时间防御措施进行分类，解释其潜在的好处和缺点，并评估图像分类的最新自适应防御能力的代表性。不幸的是，经过我们仔细的案例研究评估时，没有任何显着改善静态防御。有些甚至削弱了基本静态模型，同时增加了推理计算。尽管这些结果令人失望，但我们仍然认为自适应测试时间防御措施是一项有希望的研究途径，因此，我们为他们的彻底评估提供了建议。我们扩展了Carlini等人的清单。（2019年）通过提供针对自适应防御的具体步骤。

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.

对对抗性攻击的鲁棒性通常以对抗精度评估。但是，该指标太粗糙，无法正确捕获机器学习模型的所有鲁棒性。当对强烈的攻击进行评估时，许多防御能力并不能提供准确的改进，同时仍会部分贡献对抗性鲁棒性。流行的认证方法遇到了同一问题，因为它们提供了准确性的下限。为了捕获更精细的鲁棒性属性，我们提出了一个针对L2鲁棒性，对抗角稀疏性的新指标，该指标部分回答了“输入周围有多少个对抗性示例”的问题。我们通过评估“强”和“弱”的防御能力来证明其有用性。我们表明，一些最先进的防御能力具有非常相似的精度，在它们不强大的输入上可能具有截然不同的稀疏性。我们还表明，一些弱防御能力实际上会降低鲁棒性，而另一些防御能力则以无法捕获的准确性来加强它。这些差异可以预测这种防御与对抗性训练相结合时的实用性。

Deep learning has shown impressive performance on hard perceptual problems. However, researchers found deep learning systems to be vulnerable to small, specially crafted perturbations that are imperceptible to humans. Such perturbations cause deep learning systems to mis-classify adversarial examples, with potentially disastrous consequences where safety or security is crucial. Prior defenses against adversarial examples either targeted specific attacks or were shown to be ineffective. We propose MagNet, a framework for defending neural network classifiers against adversarial examples. MagNet neither modifies the protected classifier nor requires knowledge of the process for generating adversarial examples. MagNet includes one or more separate detector networks and a reformer network. The detector networks learn to differentiate between normal and adversarial examples by approximating the manifold of normal examples. Since they assume no specific process for generating adversarial examples, they generalize well. The reformer network moves adversarial examples towards the manifold of normal examples, which is effective for correctly classifying adversarial examples with small perturbation. We discuss the intrinsic difficulties in defending against whitebox attack and propose a mechanism to defend against graybox attack. Inspired by the use of randomness in cryptography, we use diversity to strengthen MagNet. We show empirically that Mag-Net is effective against the most advanced state-of-the-art attacks in blackbox and graybox scenarios without sacrificing false positive rate on normal examples. CCS CONCEPTS• Security and privacy → Domain-specific security and privacy architectures; • Computing methodologies → Neural networks;

删除攻击旨在通过略微扰动正确标记的训练示例的特征来大幅恶化学习模型的测试准确性。通过将这种恶意攻击正式地找到特定$ \ infty $ -wassersein球中的最坏情况培训数据，我们表明最小化扰动数据的对抗性风险相当于优化原始数据上的自然风险的上限。这意味着对抗性培训可以作为防止妄想攻击的原则防御。因此，通过普遍训练可以很大程度地回收测试精度。为了进一步了解国防的内部机制，我们披露了对抗性培训可以通过防止学习者过于依赖于自然环境中的非鲁棒特征来抵制妄想扰动。最后，我们将我们的理论调查结果与一系列关于流行的基准数据集进行了补充，这表明防御能够承受六种不同的实际攻击。在面对令人难以闻名的对手时，理论和经验结果投票给逆势训练。

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.

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.

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence. To better understand this phenomenon, we study adversarially robust learning from the viewpoint of generalization. We show that already in a simple natural data model, the sample complexity of robust learning can be significantly larger than that of "standard" learning. This gap is information theoretic and holds irrespective of the training algorithm or the model family. We complement our theoretical results with experiments on popular image classification datasets and show that a similar gap exists here as well. We postulate that the difficulty of training robust classifiers stems, at least partially, from this inherently larger sample complexity.

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.

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to normbounded attacks. However these defenses either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired privacy formalism, that provides a rigorous, generic, and flexible foundation for defense.

尽管深层神经网络在各种任务中取得了巨大的成功，但它们对不可察觉的对抗性扰动的脆弱性阻碍了他们在现实世界中的部署。最近，与随机合奏的作品相对于经过最小的计算开销的标准对手训练（AT）模型，对对抗性训练（AT）模型的对抗性鲁棒性有了显着改善，这使它们成为安全临界资源限制应用程序的有前途解决方案。但是，这种令人印象深刻的表现提出了一个问题：这些稳健性是由随机合奏提供的吗？在这项工作中，我们从理论和经验上都解决了这个问题。从理论上讲，我们首先确定通常采用的鲁棒性评估方法（例如自适应PGD）在这种情况下提供了错误的安全感。随后，我们提出了一种理论上有效的对抗攻击算法（ARC），即使在自适应PGD无法做到这一点的情况下，也能妥协随机合奏。我们在各种网络体系结构，培训方案，数据集和规范上进行全面的实验，以支持我们的主张，并经验证明，随机合奏实际上比在模型上更容易受到$ \ ell_p $结合的对抗性扰动的影响。我们的代码可以在https://github.com/hsndbk4/arc上找到。

现有针对对抗性示例（例如对抗训练）的防御能力通常假设对手将符合特定或已知的威胁模型，例如固定预算内的$ \ ell_p $扰动。在本文中，我们关注的是在训练过程中辩方假设的威胁模型中存在不匹配的情况，以及在测试时对手的实际功能。我们问一个问题：学习者是否会针对特定的“源”威胁模型进行训练，我们什么时候可以期望鲁棒性在测试时间期间概括为更强大的未知“目标”威胁模型？我们的主要贡献是通过不可预见的对手正式定义学习和概括的问题，这有助于我们从常规的对手的传统角度来理解对抗风险的增加。应用我们的框架，我们得出了将源和目标威胁模型之间的概括差距与特征提取器变化相关联的概括，该限制衡量了在给定威胁模型中提取的特征之间的预期最大差异。基于我们的概括结合，我们提出了具有变化正则化（AT-VR）的对抗训练，该训练在训练过程中降低了特征提取器在源威胁模型中的变化。我们从经验上证明，与标准的对抗训练相比，AT-VR可以改善测试时间内的概括，从而无法预见。此外，我们将变异正则化与感知对抗训练相结合[Laidlaw等。 2021]以实现不可预见的攻击的最新鲁棒性。我们的代码可在https://github.com/inspire-group/variation-regularization上公开获取。

Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to the presence of non-robust features: features (derived from patterns in the data distribution) that are highly predictive, yet brittle and (thus) incomprehensible to humans. After capturing these features within a theoretical framework, we establish their widespread existence in standard datasets. Finally, we present a simple setting where we can rigorously tie the phenomena we observe in practice to a misalignment between the (human-specified) notion of robustness and the inherent geometry of the data.

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