对抗性训练及其变体已成为使用神经网络实现对抗性稳健分类的普遍方法。但是，它的计算成本增加，以及标准性能和稳健性能之间的显着差距阻碍了进步，并提出了我们是否可以做得更好的问题。在这项工作中，我们退后一步，问：模型可以通过适当优化的集合通过标准培训来实现鲁棒性吗？为此，我们设计了一种用于鲁棒分类的元学习方法，该方法以原则性的方式在部署之前优化了数据集，并旨在有效地删除数据的非稳定部分。我们将优化方法作为内核回归的多步PGD程序进行了，其中一类核描述了无限宽的神经网（神经切线核-NTKS）。 MNIST和CIFAR-10的实验表明，当在内核回归分类器和神经网络中部署时，我们生成的数据集对PGD攻击都非常鲁棒性。但是，这种鲁棒性有些谬误，因为替代性攻击设法欺骗了模型，我们发现文献中以前的类似作品也是如此。我们讨论了这一点的潜在原因，并概述了进一步的研究途径。

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

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。

对抗性的鲁棒性已经成为深度学习的核心目标，无论是在理论和实践中。然而，成功的方法来改善对抗的鲁棒性（如逆势训练）在不受干扰的数据上大大伤害了泛化性能。这可能会对对抗性鲁棒性如何影响现实世界系统的影响（即，如果它可以提高未受干扰的数据的准确性），许多人可能选择放弃鲁棒性）。我们提出内插对抗培训，该培训最近雇用了在对抗培训框架内基于插值的基于插值的培训方法。在CiFar -10上，对抗性训练增加了标准测试错误（当没有对手时）从4.43％到12.32％，而我们的内插对抗培训我们保留了对抗性的鲁棒性，同时实现了仅6.45％的标准测试误差。通过我们的技术，强大模型标准误差的相对增加从178.1％降至仅为45.5％。此外，我们提供内插对抗性培训的数学分析，以确认其效率，并在鲁棒性和泛化方面展示其优势。

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。

Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversarial examples via a first-order method like projected gradient decent (PGD). In this paper, we make the surprising discovery that it is possible to train empirically robust models using a much weaker and cheaper adversary, an approach that was previously believed to be ineffective, rendering the method no more costly than standard training in practice. Specifically, we show that adversarial training with the fast gradient sign method (FGSM), when combined with random initialization, is as effective as PGD-based training but has significantly lower cost. Furthermore we show that FGSM adversarial training can be further accelerated by using standard techniques for efficient training of deep networks, allowing us to learn a robust CIFAR10 classifier with 45% robust accuracy to PGD attacks with = 8/255 in 6 minutes, and a robust ImageNet classifier with 43% robust accuracy at = 2/255 in 12 hours, in comparison to past work based on "free" adversarial training which took 10 and 50 hours to reach the same respective thresholds. Finally, we identify a failure mode referred to as "catastrophic overfitting" which may have caused previous attempts to use FGSM adversarial training to fail. All code for reproducing the experiments in this paper as well as pretrained model weights are at https://github.com/locuslab/fast_adversarial.

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.

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the generalization performance of the classifier. In this paper, we empirically study this phenomenon in the setting of adversarially trained deep networks, which are trained to minimize the loss under worst-case adversarial perturbations. We find that overfitting to the training set does in fact harm robust performance to a very large degree in adversarially robust training across multiple datasets (SVHN, CIFAR-10, CIFAR-100, and ImageNet) and perturbation models ( ∞ and 2 ). Based upon this observed effect, we show that the performance gains of virtually all recent algorithmic improvements upon adversarial training can be matched by simply using early stopping. We also show that effects such as the double descent curve do still occur in adversarially trained models, yet fail to explain the observed overfitting. Finally, we study several classical and modern deep learning remedies for overfitting, including regularization and data augmentation, and find that no approach in isolation improves significantly upon the gains achieved by early stopping. All code for reproducing the experiments as well as pretrained model weights and training logs can be found at https://github.com/ locuslab/robust_overfitting.

对抗性训练遭受了稳健的过度装备，这是一种现象，在训练期间鲁棒测试精度开始减少。在本文中，我们专注于通过使用常见的数据增强方案来减少强大的过度装备。我们证明，与先前的发现相反，当与模型重量平均结合时，数据增强可以显着提高鲁棒精度。此外，我们比较各种增强技术，并观察到空间组合技术适用于对抗性培训。最后，我们评估了我们在Cifar-10上的方法，而不是$ \ ell_ indty $和$ \ ell_2 $ norm-indeded扰动分别为尺寸$ \ epsilon = 8/255 $和$ \ epsilon = 128/255 $。与以前的最先进的方法相比，我们表现出+ 2.93％的绝对改善+ 2.93％，+ 2.16％。特别是，反对$ \ ell_ infty $ norm-indeded扰动尺寸$ \ epsilon = 8/255 $，我们的模型达到60.07％的强劲准确性而不使用任何外部数据。我们还通过这种方法实现了显着的性能提升，同时使用其他架构和数据集如CiFar-100，SVHN和TinyimageNet。

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.

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（DNN）容易受到对抗性示例的影响，其中DNN由于含有不可察觉的扰动而被误导为虚假输出。对抗性训练是一种可靠有效的防御方法，可能会大大减少神经网络的脆弱性，并成为强大学习的事实上的标准。尽管许多最近的作品实践了以数据为中心的理念，例如如何生成更好的对抗性示例或使用生成模型来产生额外的培训数据，但我们回顾了模型本身，并从深度特征分布的角度重新审视对抗性的鲁棒性有见地的互补性。在本文中，我们建议分支正交性对抗训练（BORT）获得最先进的性能，仅使用原始数据集用于对抗训练。为了练习我们整合多个正交解决方案空间的设计思想，我们利用一个简单明了的多分支神经网络，可消除对抗性攻击而不会增加推理时间。我们启发提出相应的损耗函数，分支 - 正交丢失，以使多支出模型正交的每个溶液空间。我们分别在CIFAR-10，CIFAR-100和SVHN上评估了我们的方法，分别针对\ ell _ {\ infty}的规范触发尺寸\ epsilon = 8/255。进行了详尽的实验，以表明我们的方法超出了所有最新方法，而无需任何技巧。与所有不使用其他数据进行培训的方法相比，我们的模型在CIFAR-10和CIFAR-100上实现了67.3％和41.5％的鲁棒精度（在最先进的ART上提高了 +7.23％和 +9.07％ ）。我们还使用比我们的训练组胜过比我们的方法的表现要大得多。我们所有的模型和代码均可在https://github.com/huangd1999/bort上在线获得。

由明确的反对派制作的对抗例子在机器学习中引起了重要的关注。然而，潜在虚假朋友带来的安全风险基本上被忽视了。在本文中，我们揭示了虚伪的例子的威胁 - 最初被错误分类但是虚假朋友扰乱的投入，以强迫正确的预测。虽然这种扰动的例子似乎是无害的，但我们首次指出，它们可能是恶意地用来隐瞒评估期间不合格（即，不如所需）模型的错误。一旦部署者信任虚伪的性能并在真实应用程序中应用“良好的”模型，即使在良性环境中也可能发生意外的失败。更严重的是，这种安全风险似乎是普遍存在的：我们发现许多类型的不合标准模型易受多个数据集的虚伪示例。此外，我们提供了第一次尝试，以称为虚伪风险的公制表征威胁，并试图通过一些对策来规避它。结果表明对策的有效性，即使在自适应稳健的培训之后，风险仍然是不可忽视的。

神经网络容易受到对抗性攻击的影响：为其输入添加良好的难以察觉的扰动可以修改它们的输出。对抗性培训是针对这种攻击训练强大模型的最有效的方法之一。然而，它比Vanilla训练的神经网络训练慢得多，因为它需要在每次迭代时构建整个训练数据的对抗性示例，这阻碍了其有效性。最近，提出了快速的对抗培训，可以有效地获得强大的模型。然而，其成功背后的原因尚未完全理解，更重要的是，它只能为$ \ ell_ \ infty $ -bounded攻击培训强大的模型，因为它在训练期间使用FGSM。在本文中，通过利用Coreset选择理论，我们展示了如何选择小型培训数据的子集，以减少强大培训的时间复杂性提供更原则的方法。与现有方法不同，我们的方法可以适应各种各样的培训目标，包括交易，$ \ ell_p $ -pgd和感知对抗培训。我们的实验结果表明，我们的方法将对抗性训练速度升高2-3次，同时经历清洁和稳健的准确性的少量减少。

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。

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.

许多最先进的对抗性培训方法利用对抗性损失的上限来提供安全保障。然而，这些方法需要在每个训练步骤中计算，该步骤不能包含在梯度中的梯度以进行反向化。我们基于封闭形式的对抗性损失的封闭溶液引入了一种新的更具内容性的对抗性培训，可以有效地培养了背部衰退。通过稳健优化的最先进的工具促进了这一界限。我们使用我们的方法推出了两种新方法。第一种方法（近似稳健的上限或arub）使用网络的第一阶近似以及来自线性鲁棒优化的基本工具，以获得可以容易地实现的对抗丢失的近似偏置。第二种方法（鲁棒上限或摩擦）计算对抗性损失的精确上限。在各种表格和视觉数据集中，我们展示了我们更加原则的方法的有效性 - 摩擦比最先进的方法更强大，而是较大的扰动的最新方法，而谷会匹配的性能 - 小扰动的艺术方法。此外，摩擦和灌注速度比标准对抗性培训快（以牺牲内存增加）。重现结果的所有代码都可以在https://github.com/kimvc7/trobustness找到。

对抗性例子的现象说明了深神经网络最基本的漏洞之一。在推出这一固有的弱点的各种技术中，对抗性训练已成为学习健壮模型的最有效策略。通常，这是通过平衡强大和自然目标来实现的。在这项工作中，我们旨在通过执行域不变的功能表示，进一步优化鲁棒和标准准确性之间的权衡。我们提出了一种新的对抗训练方法，域不变的对手学习（DIAL），该方法学习了一个既健壮又不变的功能表示形式。拨盘使用自然域及其相应的对抗域上的域对抗神经网络（DANN）的变体。在源域由自然示例组成和目标域组成的情况下，是对抗性扰动的示例，我们的方法学习了一个被限制的特征表示，以免区分自然和对抗性示例，因此可以实现更强大的表示。拨盘是一种通用和模块化技术，可以轻松地将其纳入任何对抗训练方法中。我们的实验表明，将拨号纳入对抗训练过程中可以提高鲁棒性和标准精度。

在本讨论文件中，我们调查了有关机器学习模型鲁棒性的最新研究。随着学习算法在数据驱动的控制系统中越来越流行，必须确保它们对数据不确定性的稳健性，以维持可靠的安全至关重要的操作。我们首先回顾了这种鲁棒性的共同形式主义，然后继续讨论训练健壮的机器学习模型的流行和最新技术，以及可证明这种鲁棒性的方法。从强大的机器学习的这种统一中，我们识别并讨论了该地区未来研究的迫切方向。

Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models. However, it is conservative or even pessimistic so that it sometimes hurts the natural generalization. In this paper, we raise a fundamental question-do we have to trade off natural generalization for adversarial robustness? We argue that adversarial training is to employ confident adversarial data for updating the current model. We propose a novel formulation of friendly adversarial training (FAT): rather than employing most adversarial data maximizing the loss, we search for least adversarial data (i.e., friendly adversarial data) minimizing the loss, among the adversarial data that are confidently misclassified. Our novel formulation is easy to implement by just stopping the most adversarial data searching algorithms such as PGD (projected gradient descent) early, which we call early-stopped PGD. Theoretically, FAT is justified by an upper bound of the adversarial risk. Empirically, early-stopped PGD allows us to answer the earlier question negatively-adversarial robustness can indeed be achieved without compromising the natural generalization.* Equal contribution † Preliminary work was done during an internship at RIKEN AIP.