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。
translated by 谷歌翻译
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。
translated by 谷歌翻译
The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years. Among them, adversarial training is the most promising one, which flattens the input loss landscape (loss change with respect to input) via training on adversarially perturbed examples. However, how the widely used weight loss landscape (loss change with respect to weight) performs in adversarial training is rarely explored. In this paper, we investigate the weight loss landscape from a new perspective, and identify a clear correlation between the flatness of weight loss landscape and robust generalization gap. Several well-recognized adversarial training improvements, such as early stopping, designing new objective functions, or leveraging unlabeled data, all implicitly flatten the weight loss landscape. Based on these observations, we propose a simple yet effective Adversarial Weight Perturbation (AWP) to explicitly regularize the flatness of weight loss landscape, forming a double-perturbation mechanism in the adversarial training framework that adversarially perturbs both inputs and weights. Extensive experiments demonstrate that AWP indeed brings flatter weight loss landscape and can be easily incorporated into various existing adversarial training methods to further boost their adversarial robustness.
translated by 谷歌翻译
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。
translated by 谷歌翻译
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 $扰动。在本文中,我们关注的是在训练过程中辩方假设的威胁模型中存在不匹配的情况,以及在测试时对手的实际功能。我们问一个问题:学习者是否会针对特定的“源”威胁模型进行训练,我们什么时候可以期望鲁棒性在测试时间期间概括为更强大的未知“目标”威胁模型?我们的主要贡献是通过不可预见的对手正式定义学习和概括的问题,这有助于我们从常规的对手的传统角度来理解对抗风险的增加。应用我们的框架,我们得出了将源和目标威胁模型之间的概括差距与特征提取器变化相关联的概括,该限制衡量了在给定威胁模型中提取的特征之间的预期最大差异。基于我们的概括结合,我们提出了具有变化正则化(AT-VR)的对抗训练,该训练在训练过程中降低了特征提取器在源威胁模型中的变化。我们从经验上证明,与标准的对抗训练相比,AT-VR可以改善测试时间内的概括,从而无法预见。此外,我们将变异正则化与感知对抗训练相结合[Laidlaw等。 2021]以实现不可预见的攻击的最新鲁棒性。我们的代码可在https://github.com/inspire-group/variation-regularization上公开获取。
translated by 谷歌翻译
在对抗文献中,鲁棒性和准确性之间的权衡得到了广泛的研究。尽管仍然有争议,但普遍的观点是,从经验或理论上,这种权衡是固有的。因此,我们在对抗训练中挖掘了这种权衡的起源,发现它可能源于不当定义的可靠错误,该错误施加了局部不变性的诱导偏见 - 对平稳性的过度校正。鉴于此,我们主张采用局部模棱两可来描述健壮模型的理想行为,从而导致自洽的强大错误称为得分。根据定义,得分有助于稳健性与准确性之间的对帐,同时仍通过稳健优化处理最坏情况的不确定性。通过简单地将KL差异替换为距离指标的变体,得分可以有效地最小化。从经验上讲,我们的模型在AutoAttact下的强力板上实现了最高的性能。此外,得分提供了指导性见解,以解释在健壮模型上观察到的过度拟合现象和语义输入梯度。代码可在https://github.com/p2333/score上找到。
translated by 谷歌翻译
尽管深层神经网络在各种任务中取得了巨大的成功,但它们对不可察觉的对抗性扰动的脆弱性阻碍了他们在现实世界中的部署。最近,与随机合奏的作品相对于经过最小的计算开销的标准对手训练(AT)模型,对对抗性训练(AT)模型的对抗性鲁棒性有了显着改善,这使它们成为安全临界资源限制应用程序的有前途解决方案。但是,这种令人印象深刻的表现提出了一个问题:这些稳健性是由随机合奏提供的吗?在这项工作中,我们从理论和经验上都解决了这个问题。从理论上讲,我们首先确定通常采用的鲁棒性评估方法(例如自适应PGD)在这种情况下提供了错误的安全感。随后,我们提出了一种理论上有效的对抗攻击算法(ARC),即使在自适应PGD无法做到这一点的情况下,也能妥协随机合奏。我们在各种网络体系结构,培训方案,数据集和规范上进行全面的实验,以支持我们的主张,并经验证明,随机合奏实际上比在模型上更容易受到$ \ ell_p $结合的对抗性扰动的影响。我们的代码可以在https://github.com/hsndbk4/arc上找到。
translated by 谷歌翻译
普遍认为对抗培训是一种可靠的方法来改善对抗对抗攻击的模型稳健性。但是,在本文中,我们表明,当训练在一种类型的中毒数据时,对抗性培训也可以被愚蠢地具有灾难性行为,例如,$ <1 \%$强大的测试精度,以$> 90 \%$强大的训练准确度在CiFar-10数据集上。以前,在培训数据中,已经成功愚弄了标准培训($ 15.8 \%$标准测试精度,在CIFAR-10数据集中的标准训练准确度为99.9美元,但它们的中毒可以很容易地删除采用对抗性培训。因此,我们的目标是设计一种名为Advin的新型诱导噪声,这是一种不可动摇的培训数据中毒。 Advin不仅可以通过大幅度的利润率降低对抗性培训的鲁棒性,例如,从Cifar-10数据集每次为0.57 \%$ 0.57 \%$ 0.57 \%$ 0.1,但也有效地愚弄标准培训($ 13.1 \%$标准测试准确性$ 100 \%$标准培训准确度)。此外,否则可以应用于防止个人数据(如SELYIES)在没有授权的情况下剥削,无论是标准还是对抗性培训。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
对抗性可转移性是一种有趣的性质 - 针对一个模型制作的对抗性扰动也是对另一个模型有效的,而这些模型来自不同的模型家庭或培训过程。为了更好地保护ML系统免受对抗性攻击,提出了几个问题:对抗性转移性的充分条件是什么,以及如何绑定它?有没有办法降低对抗的转移性,以改善合奏ML模型的鲁棒性?为了回答这些问题,在这项工作中,我们首先在理论上分析和概述了模型之间的对抗性可转移的充分条件;然后提出一种实用的算法,以减少集合内基础模型之间的可转换,以提高其鲁棒性。我们的理论分析表明,只有促进基础模型梯度之间的正交性不足以确保低可转移性;与此同时,模型平滑度是控制可转移性的重要因素。我们还在某些条件下提供了对抗性可转移性的下界和上限。灵感来自我们的理论分析,我们提出了一种有效的可转让性,减少了平滑(TRS)集合培训策略,以通过实施基础模型之间的梯度正交性和模型平滑度来培训具有低可转换性的强大集成。我们对TRS进行了广泛的实验,并与6个最先进的集合基线进行比较,防止不同数据集的8个白箱攻击,表明所提出的TRS显着优于所有基线。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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
translated by 谷歌翻译
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).
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
对抗训练(AT)在防御对抗例子方面表现出色。最近的研究表明,示例对于AT期间模型的最终鲁棒性并不同样重要,即,所谓的硬示例可以攻击容易表现出比对最终鲁棒性的鲁棒示例更大的影响。因此,保证硬示例的鲁棒性对于改善模型的最终鲁棒性至关重要。但是,定义有效的启发式方法来寻找辛苦示例仍然很困难。在本文中,受到信息瓶颈(IB)原则的启发,我们发现了一个具有高度共同信息及其相关的潜在表示的例子,更有可能受到攻击。基于此观察,我们提出了一种新颖有效的对抗训练方法(Infoat)。鼓励Infoat找到具有高相互信息的示例,并有效利用它们以提高模型的最终鲁棒性。实验结果表明,与几种最先进的方法相比,Infoat在不同数据集和模型之间达到了最佳的鲁棒性。
translated by 谷歌翻译
许多最先进的ML模型在各种任务中具有优于图像分类的人类。具有如此出色的性能,ML模型今天被广泛使用。然而,存在对抗性攻击和数据中毒攻击的真正符合ML模型的稳健性。例如,Engstrom等人。证明了最先进的图像分类器可以容易地被任意图像上的小旋转欺骗。由于ML系统越来越纳入安全性和安全敏感的应用,对抗攻击和数据中毒攻击构成了相当大的威胁。本章侧重于ML安全的两个广泛和重要的领域:对抗攻击和数据中毒攻击。
translated by 谷歌翻译
作为反对攻击的最有效的防御方法之一,对抗性训练倾向于学习包容性的决策边界,以提高深度学习模型的鲁棒性。但是,由于沿对抗方向的边缘的大幅度和不必要的增加,对抗性训练会在自然实例和对抗性示例之间引起严重的交叉,这不利于平衡稳健性和自然准确性之间的权衡。在本文中,我们提出了一种新颖的对抗训练计划,以在稳健性和自然准确性之间进行更好的权衡。它旨在学习一个中度包容的决策边界,这意味着决策边界下的自然示例的边缘是中等的。我们称此方案为中等边缘的对抗训练(MMAT),该方案生成更细粒度的对抗示例以减轻交叉问题。我们还利用了经过良好培训的教师模型的逻辑来指导我们的模型学习。最后,MMAT在Black-Box和White-Box攻击下都可以实现高自然的精度和鲁棒性。例如,在SVHN上,实现了最新的鲁棒性和自然精度。
translated by 谷歌翻译