尽管深度神经网络(DNN)在感知和控制任务中表现出令人难以置信的性能,但几个值得信赖的问题仍然是开放的。其中一个最讨论的主题是存在对抗扰动的存在,它在能够量化给定输入的稳健性的可提供技术上开辟了一个有趣的研究线。在这方面,来自分类边界的输入的欧几里德距离表示良好被证明的鲁棒性评估,作为最小的经济适用的逆势扰动。不幸的是,由于NN的非凸性质,计算如此距离非常复杂。尽管已经提出了几种方法来解决这个问题,但据我们所知,没有提出可证明的结果来估计和绑定承诺的错误。本文通过提出两个轻量级策略来寻找最小的对抗扰动来解决这个问题。不同于现有技术,所提出的方法允许与理论上的近似距离的误差估计理论配制。最后,据报道,据报道了大量实验来评估算法的性能并支持理论发现。所获得的结果表明,该策略近似于靠近分类边界的样品的理论距离,导致可提供对任何对抗攻击的鲁棒性保障。
translated by 谷歌翻译
由于存在对抗性攻击,因此在安全至关重要系统中使用神经网络需要安全,可靠的模型。了解任何输入X的最小对抗扰动,或等效地知道X与分类边界的距离,可以评估分类鲁棒性,从而提供可认证的预测。不幸的是,计算此类距离的最新技术在计算上很昂贵,因此不适合在线应用程序。这项工作提出了一个新型的分类器家族,即签名的距离分类器(SDC),从理论的角度来看,它直接输出X与分类边界的确切距离,而不是概率分数(例如SoftMax)。 SDC代表一个强大的设计分类器家庭。为了实际解决SDC的理论要求,提出了一种名为Unitary级别神经网络的新型网络体系结构。实验结果表明,所提出的体系结构近似于签名的距离分类器,因此允许以单个推断为代价对X进行在线认证分类。
translated by 谷歌翻译
We propose a method to learn deep ReLU-based classifiers that are provably robust against normbounded adversarial perturbations on the training data. For previously unseen examples, the approach is guaranteed to detect all adversarial examples, though it may flag some non-adversarial examples as well. The basic idea is to consider a convex outer approximation of the set of activations reachable through a norm-bounded perturbation, and we develop a robust optimization procedure that minimizes the worst case loss over this outer region (via a linear program). Crucially, we show that the dual problem to this linear program can be represented itself as a deep network similar to the backpropagation network, leading to very efficient optimization approaches that produce guaranteed bounds on the robust loss. The end result is that by executing a few more forward and backward passes through a slightly modified version of the original network (though possibly with much larger batch sizes), we can learn a classifier that is provably robust to any norm-bounded adversarial attack. We illustrate the approach on a number of tasks to train classifiers with robust adversarial guarantees (e.g. for MNIST, we produce a convolutional classifier that provably has less than 5.8% test error for any adversarial attack with bounded ∞ norm less than = 0.1), and code for all experiments is available at http://github.com/ locuslab/convex_adversarial.
translated by 谷歌翻译
Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed and added to the input to make the target model produce erroneous output. Most of the existing studies on generating adversarial perturbations attempt to perturb the entire input indiscriminately. In this paper, we propose ExploreADV, a general and flexible adversarial attack system that is capable of modeling regional and imperceptible attacks, allowing users to explore various kinds of adversarial examples as needed. We adapt and combine two existing boundary attack methods, DeepFool and Brendel\&Bethge Attack, and propose a mask-constrained adversarial attack system, which generates minimal adversarial perturbations under the pixel-level constraints, namely ``mask-constraints''. We study different ways of generating such mask-constraints considering the variance and importance of the input features, and show that our adversarial attack system offers users good flexibility to focus on sub-regions of inputs, explore imperceptible perturbations and understand the vulnerability of pixels/regions to adversarial attacks. We demonstrate our system to be effective based on extensive experiments and user study.
translated by 谷歌翻译
由于机器学习(ML)系统变得普遍存在,因此保护其安全性至关重要。然而,最近已经证明,动机的对手能够通过使用语义转换扰乱测试数据来误导ML系统。虽然存在丰富的研究机构,但为ML模型提供了可提供的稳健性保证,以防止$ \ ell_p $ norm界限对抗对抗扰动,抵御语义扰动的保证仍然很广泛。在本文中,我们提供了TSS - 一种统一的框架,用于针对一般对抗性语义转换的鲁棒性认证。首先,根据每个转换的性质,我们将常见的变换划分为两类,即可解决的(例如,高斯模糊)和差异可解的(例如,旋转)变换。对于前者,我们提出了特定于转型的随机平滑策略并获得强大的稳健性认证。后者类别涵盖涉及插值错误的变换,我们提出了一种基于分层采样的新方法,以证明稳健性。我们的框架TSS利用这些认证策略并结合了一致性增强的培训,以提供严谨的鲁棒性认证。我们对十种挑战性语义转化进行了广泛的实验,并表明TSS显着优于现有技术。此外,据我们所知,TSS是第一种在大规模想象数据集上实现非竞争认证稳健性的方法。例如,我们的框架在ImageNet上实现了旋转攻击的30.4%认证的稳健准确性(在$ \ PM 30 ^ \ CIC $)。此外,要考虑更广泛的转换,我们展示了TSS对自适应攻击和不可预见的图像损坏,例如CIFAR-10-C和Imagenet-C。
translated by 谷歌翻译
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。
translated by 谷歌翻译
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the importance of this phenomenon, no effective methods have been proposed to accurately compute the robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets. In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show that our approach outperforms recent methods in the task of computing adversarial perturbations and making classifiers more robust. 1
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
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
学习证明(POL)建议模型所有者使用机器学习培训检查站,以建立已经花费了必要的培训计算的证明。 POL FIREGO加密方法和贸易严格的安全性的作者通过适用于随机梯度下降和适应性变体,可扩展到深度学习。缺乏正式分析使攻击者可能能够为他们没有训练的模型提供证据。我们对为什么不能正式(DIS)正式分析POL协议可抵抗欺骗对手。为此,我们在POL中解开了证明验证的两个角色:(a)有效确定证明是否是有效的梯度下降轨迹,以及(b)确定优先级,使在培训完成后制作证明(即。 ,欺骗)。我们表明,有效的验证会导致接受合法证明和拒绝无效的证据之间的权衡,因为深度学习必然涉及噪音。没有针对这种噪声如何影响训练的精确分析模型,我们无法正式保证POL验证算法是否强大。然后,我们证明,建立优先级也可以鲁棒化地减少到学习理论中的一个开放问题:欺骗Pol Pol hoc hoc训练类似于在非凸X学习中找到具有相同终点的不同轨迹。但是,我们不严格地知道对最终模型权重的先验知识是否有助于发现此类轨迹。我们得出的结论是,在解决上述开放问题之前,可能需要更严重地依靠密码学来制定新的POL协议,并提供正式的鲁棒性保证。特别是,这将有助于建立优先级。作为我们分析的见解的副产品,我们还展示了对POL的两次新攻击。
translated by 谷歌翻译
人工神经网络(ANN)训练景观的非凸起带来了固有的优化困难。虽然传统的背传播随机梯度下降(SGD)算法及其变体在某些情况下是有效的,但它们可以陷入杂散的局部最小值,并且对初始化和普通公共表敏感。最近的工作表明,随着Relu激活的ANN的培训可以重新重整为凸面计划,使希望能够全局优化可解释的ANN。然而,天真地解决凸训练制剂具有指数复杂性,甚至近似启发式需要立方时间。在这项工作中,我们描述了这种近似的质量,并开发了两个有效的算法,这些算法通过全球收敛保证培训。第一算法基于乘法器(ADMM)的交替方向方法。它解决了精确的凸形配方和近似对应物。实现线性全局收敛,并且初始几次迭代通常会产生具有高预测精度的解决方案。求解近似配方时,每次迭代时间复杂度是二次的。基于“采样凸面”理论的第二种算法更简单地实现。它解决了不受约束的凸形制剂,并收敛到大约全球最佳的分类器。当考虑对抗性培训时,ANN训练景观的非凸起加剧了。我们将稳健的凸优化理论应用于凸训练,开发凸起的凸起制剂,培训Anns对抗对抗投入。我们的分析明确地关注一个隐藏层完全连接的ANN,但可以扩展到更复杂的体系结构。
translated by 谷歌翻译
Riemannian优化是解决优化问题的原则框架,其中所需的最佳被限制为光滑的歧管$ \ Mathcal {M} $。在此框架中设计的算法通常需要对歧管的几何描述,该描述通常包括切线空间,缩回和成本函数的梯度。但是,在许多情况下,由于缺乏信息或棘手的性能,只能访问这些元素的子集(或根本没有)。在本文中,我们提出了一种新颖的方法,可以在这种情况下执行近似Riemannian优化,其中约束歧管是$ \ r^{d} $的子手机。至少,我们的方法仅需要一组无噪用的成本函数$(\ x_ {i},y_ {i})\ in {\ mathcal {m}} \ times \ times \ times \ times \ times \ mathbb {r} $和内在的歧管$ \ MATHCAL {M} $的维度。使用样品,并利用歧管-MLS框架(Sober和Levin 2020),我们构建了缺少的组件的近似值,这些组件娱乐可证明的保证并分析其计算成本。如果某些组件通过分析给出(例如,如果成本函数及其梯度明确给出,或者可以计算切线空间),则可以轻松地适应该算法以使用准确的表达式而不是近似值。我们使用我们的方法分析了基于Riemannian梯度的方法的全球收敛性,并从经验上证明了该方法的强度,以及基于类似原理的共轭梯度类型方法。
translated by 谷歌翻译
Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs. However, popular explanations methods have been found to be fragile to minor perturbations of input features or model parameters. Relying on constraint relaxation techniques from non-convex optimization, we develop a method that upper-bounds the largest change an adversary can make to a gradient-based explanation via bounded manipulation of either the input features or model parameters. By propagating a compact input or parameter set as symbolic intervals through the forwards and backwards computations of the neural network we can formally certify the robustness of gradient-based explanations. Our bounds are differentiable, hence we can incorporate provable explanation robustness into neural network training. Empirically, our method surpasses the robustness provided by previous heuristic approaches. We find that our training method is the only method able to learn neural networks with certificates of explanation robustness across all six datasets tested.
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
时间序列数据在许多现实世界中(例如,移动健康)和深神经网络(DNNS)中产生,在解决它们方面已取得了巨大的成功。尽管他们成功了,但对他们对对抗性攻击的稳健性知之甚少。在本文中,我们提出了一个通过统计特征(TSA-STAT)}称为时间序列攻击的新型对抗框架}。为了解决时间序列域的独特挑战,TSA-STAT对时间序列数据的统计特征采取限制来构建对抗性示例。优化的多项式转换用于创建比基于加性扰动的攻击(就成功欺骗DNN而言)更有效的攻击。我们还提供有关构建对抗性示例的统计功能规范的认证界限。我们对各种现实世界基准数据集的实验表明,TSA-STAT在欺骗DNN的时间序列域和改善其稳健性方面的有效性。 TSA-STAT算法的源代码可在https://github.com/tahabelkhouja/time-series-series-attacks-via-statity-features上获得
translated by 谷歌翻译
在深度学习中的优化分析是连续的,专注于(变体)梯度流动,或离散,直接处理(变体)梯度下降。梯度流程可符合理论分析,但是风格化并忽略计算效率。它代表梯度下降的程度是深度学习理论的一个开放问题。目前的论文研究了这个问题。将梯度下降视为梯度流量初始值问题的近似数值问题,发现近似程度取决于梯度流动轨迹周围的曲率。然后,我们表明,在具有均匀激活的深度神经网络中,梯度流动轨迹享有有利的曲率,表明它们通过梯度下降近似地近似。该发现允许我们将深度线性神经网络的梯度流分析转换为保证梯度下降,其几乎肯定会在随机初始化下有效地收敛到全局最小值。实验表明,在简单的深度神经网络中,具有传统步长的梯度下降确实接近梯度流。我们假设梯度流动理论将解开深入学习背后的奥秘。
translated by 谷歌翻译
深入学习在现代分类任务中取得了许多突破。已经提出了众多架构用于不同的数据结构,但是当涉及丢失功能时,跨熵损失是主要的选择。最近,若干替代损失已经看到了深度分类器的恢复利益。特别是,经验证据似乎促进了方形损失,但仍然缺乏理论效果。在这项工作中,我们通过系统地研究了在神经切线内核(NTK)制度中的过度分化的神经网络的表现方式来促进对分类方面损失的理论理解。揭示了关于泛化误差,鲁棒性和校准错误的有趣特性。根据课程是否可分离,我们考虑两种情况。在一般的不可分类案例中,为错误分类率和校准误差建立快速收敛速率。当类是可分离的时,错误分类率改善了速度快。此外,经过证明得到的余量被证明是低于零的较低,提供了鲁棒性的理论保证。我们希望我们的调查结果超出NTK制度并转化为实际设置。为此,我们对实际神经网络进行广泛的实证研究,展示了合成低维数据和真实图像数据中方损的有效性。与跨熵相比,方形损耗具有可比的概括误差,但具有明显的鲁棒性和模型校准的优点。
translated by 谷歌翻译
在本文中,我们启动了对分类中低维对逆动力(LDAP)现象的严格研究。与经典设置不同,这些扰动仅限于尺寸$ k $的子空间,该子空间比功能空间的尺寸$ d $小得多。 $ k = 1 $的情况对应于所谓的通用对抗扰动(UAPS; Moosavi-Dezfooli等,2017)。首先,我们考虑在通用规律条件(包括RELU网络)下的二进制分类器,并根据任何子空间的愚蠢率计算分析下限。这些界限明确强调了愚蠢率对模型的点缘的依赖性(即,在测试点的输出与其梯度的$ L_2 $ norm的比率),以及给定子空间与该梯度的对齐模型W.R.T.的梯度输入。我们的结果为启发式方法的最新成功提供了有效产生低维对对抗性扰动的严格解释。最后,我们表明,如果决策区域紧凑,那么它将接受通用的对抗性扰动,其$ l_2 $ norm,比典型的$ \ sqrt {d} $倍乘以数据点的典型$ l_2 $ norm。我们的理论结果通过对合成和真实数据的实验证实。
translated by 谷歌翻译
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。
translated by 谷歌翻译