在过去的几年中,对抗性示例的检测一直是一个热门话题,因为它对于在关键应用程序中安全部署机器学习算法的重要性。但是,通常通过假设一个隐式已知的攻击策略来验证检测方法,这不一定要考虑现实生活中的威胁。确实,这可能导致对检测器性能的过度评估,并可能在竞争检测方案之间的比较中引起一些偏见。我们提出了一个新型的多武器框架,称为Mead,用于根据几种攻击策略来评估探测器,以克服这一限制。其中,我们利用三个新目标来产生攻击。所提出的性能指标基于最坏的情况:仅当正确识别所有不同攻击时,检测才成功。从经验上讲,我们展示了方法的有效性。此外,最先进的探测器获得的表现不佳,为一项新的令人兴奋的研究开放。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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。
translated by 谷歌翻译
深度学习中的关键挑战之一是检测对抗例的有效策略的定义。为此,我们提出了一种名为Ensemble对抗探测器(EAD)的新型方法,用于识别对抗性示例,在标准的多字节分类场景中。 EAD结合了多个检测器,该检测器利用了预先训练的深神经网络(DNN)内部表示中的输入实例的不同属性。具体而言,EAD基于Mahalanobis距离和局部内在的维度(盖子)与基于单级支持向量机(OSVM)的新引进的方法集成了最先进的探测器。尽管所有构成方法都假定测试实例从一组正确分类的训练实例的距离越大,但概率越高,其是对手示例的概率越高,它们在计算距离的方式中不同。为了利用不同方法的有效性在捕获数据分布的不同特性,因此,有效地解决泛化和过度装备之间的权衡,EAD采用探测器特定的距离分数作为逻辑回归分类器的特征,独立的超公数后优化。我们在不同的数据集(CIFAR-10,CiFar-100和SVHN)和模型(Reset和Densenet)上评估了EAD方法,以及通过与竞争方法进行比较,关于四个对抗性攻击(FGSM,BIM,DeepFool和CW)。总的来说,我们表明EAD达到了最大的Auroc和Aupr在大多数设置和其他方面的表现。对现有技术的改进以及容易延伸EAD以包括任何任意探测器的可能性,铺平了在普遍示例性检测的广场上广泛采用的集合方法。
translated by 谷歌翻译
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.
translated by 谷歌翻译
深度学习(DL)系统的安全性是一个极为重要的研究领域,因为它们正在部署在多个应用程序中,因为它们不断改善,以解决具有挑战性的任务。尽管有压倒性的承诺,但深度学习系统容易受到制作的对抗性例子的影响,这可能是人眼无法察觉的,但可能会导致模型错误分类。对基于整体技术的对抗性扰动的保护已被证明很容易受到更强大的对手的影响,或者证明缺乏端到端评估。在本文中,我们试图开发一种新的基于整体的解决方案,该解决方案构建具有不同决策边界的防御者模型相对于原始模型。通过(1)通过一种称为拆分和剃须的方法转换输入的分类器的合奏,以及(2)通过一种称为对比度功能的方法限制重要特征,显示出相对于相对于不同的梯度对抗性攻击,这减少了将对抗性示例从原始示例转移到针对同一类的防御者模型的机会。我们使用标准图像分类数据集(即MNIST,CIFAR-10和CIFAR-100)进行了广泛的实验,以实现最新的对抗攻击,以证明基于合奏的防御的鲁棒性。我们还在存在更强大的对手的情况下评估稳健性,该对手同时靶向合奏中的所有模型。已经提供了整体假阳性和误报的结果,以估计提出的方法的总体性能。
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
随着在图像识别中的快速进步和深度学习模型的使用,安全成为他们在安全关键系统中部署的主要关注点。由于深度学习模型的准确性和稳健性主要归因于训练样本的纯度,因此深度学习架构通常易于对抗性攻击。通过对正常图像进行微妙的扰动来获得对抗性攻击,这主要是人类,但可以严重混淆最先进的机器学习模型。什么特别的智能扰动或噪声在正常图像上添加了它导致深神经网络的灾难性分类?使用统计假设检测,我们发现条件变形自身偏析器(CVAE)令人惊讶地擅长检测难以察觉的图像扰动。在本文中,我们展示了CVAE如何有效地用于检测对图像分类网络的对抗攻击。我们展示了我们的成果,Cifar-10数据集,并展示了我们的方法如何为先前的方法提供可比性,以检测对手,同时不会与嘈杂的图像混淆,其中大多数现有方法都摇摇欲坠。
translated by 谷歌翻译
对抗性的鲁棒性已成为机器学习越来越兴趣的话题,因为观察到神经网络往往会变得脆弱。我们提出了对逆转防御的信息几何表述,并引入Fire,这是一种针对分类跨透明镜损失的新的Fisher-Rao正则化,这基于对应于自然和受扰动输入特征的软磁输出之间的测量距离。基于SoftMax分布类的信息几何特性,我们为二进制和多类案例提供了Fisher-Rao距离(FRD)的明确表征,并绘制了一些有趣的属性以及与标准正则化指标的连接。此外,对于一个简单的线性和高斯模型,我们表明,在精度 - 舒适性区域中的所有帕累托最佳点都可以通过火力达到,而其他最先进的方法则可以通过火灾。从经验上讲,我们评估了经过标准数据集拟议损失的各种分类器的性能,在清洁和健壮的表现方面同时提高了1 \%的改进,同时将培训时间降低了20 \%,而不是表现最好的方法。
translated by 谷歌翻译
基于深度神经网络的医学图像系统容易受到对抗的例子。在文献中提出了许多防御机制,然而,现有的防御者假设被动攻击者对防御系统知之甚少,并没有根据防御改变攻击战略。最近的作品表明,一个强大的自适应攻击,攻击者被认为具有完全了解防御系统的知识,可以轻松绕过现有的防御。在本文中,我们提出了一种名为Medical Aegis的新型对抗性示例防御系统。据我们所知,医疗AEGIS是文献中的第一次防范,成功地解决了对医学图像的强烈适应性的对抗性示例攻击。医疗AEGIS拥有两层保护剂:第一层垫通过去除其高频分量而削弱了攻击的对抗性操纵能力,但对原始图像的分类性能构成了最小的影响;第二层盾牌学习一组每级DNN模型来预测受保护模型的登录。偏离屏蔽的预测表明对抗性示例。盾牌受到在我们的压力测试中的观察中的观察,即在DNN模型的浅层中存在坚固的小径,自适应攻击难以破坏。实验结果表明,建议的防御精确地检测了自适应攻击,模型推理的开销具有可忽略的开销。
translated by 谷歌翻译
Adversarial attacks pose safety and security concerns to deep learning applications, but their characteristics are under-explored. Yet largely imperceptible, a strong trace could have been left by PGD-like attacks in an adversarial example. Recall that PGD-like attacks trigger the ``local linearity'' of a network, which implies different extents of linearity for benign or adversarial examples. Inspired by this, we construct an Adversarial Response Characteristics (ARC) feature to reflect the model's gradient consistency around the input to indicate the extent of linearity. Under certain conditions, it qualitatively shows a gradually varying pattern from benign example to adversarial example, as the latter leads to Sequel Attack Effect (SAE). To quantitatively evaluate the effectiveness of ARC, we conduct experiments on CIFAR-10 and ImageNet for attack detection and attack type recognition in a challenging setting. The results suggest that SAE is an effective and unique trace of PGD-like attacks reflected through the ARC feature. The ARC feature is intuitive, light-weighted, non-intrusive, and data-undemanding.
translated by 谷歌翻译
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;
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
The authors thank Nicholas Carlini (UC Berkeley) and Dimitris Tsipras (MIT) for feedback to improve the survey quality. We also acknowledge X. Huang (Uni. Liverpool), K. R. Reddy (IISC), E. Valle (UNICAMP), Y. Yoo (CLAIR) and others for providing pointers to make the survey more comprehensive.
translated by 谷歌翻译
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。
translated by 谷歌翻译
已知深度学习模型容易受到针对恶意目的设计的对抗性例子的影响,并且对人类感知系统是无法察觉的。自动编码器仅在良性示例上接受训练时,已广泛用于(自我监管的)对抗检测,基于以下假设,即对抗性示例会产生较大的重建误差。但是,由于其训练中缺乏对抗性示例和自动编码器的过于强大的概括能力,因此在实践中,这种假设并不总是成立的。为了减轻这个问题,我们探索如何在自动编码器结构下使用分离的标签/语义特征检测对抗性示例。具体而言,我们提出了基于删除表示的重建(DRR)。在DRR中,我们对正确配对的标签/语义功能和错误配对的标签/语义功能进行训练,以重建良性和反描述。这模仿了对抗性示例的行为,并可以降低自动编码器的不必要的概括能力。我们将我们的方法与不同的对抗性攻击和不同受害者模型下的最先进的自我监督检测方法进行了比较,并且在各种指标(ROC曲线下的区域,真实的正率和真实的负率)中表现出更好的性能)对于大多数攻击设置。尽管DRR最初是为视觉任务设计的,但我们证明它也可以轻松扩展到自然语言任务。值得注意的是,与其他基于自动编码器的检测器不同,我们的方法可以为自适应对手提供抗性。
translated by 谷歌翻译
检测分配(OOD)输入对于安全部署现实世界的深度学习模型至关重要。在评估良性分布和OOD样品时,检测OOD示例的现有方法很好。然而,在本文中,我们表明,当在分发的分布和OOD输入时,现有的检测机制可以极其脆弱,其具有最小的对抗扰动,这不会改变其语义。正式地,我们广泛地研究了对共同的检测方法的强大分布检测问题,并表明最先进的OOD探测器可以通过对分布和ood投入增加小扰动来容易地欺骗。为了抵消这些威胁,我们提出了一种称为芦荟的有效算法,它通过将模型暴露于对抗性inlier和异常值示例来执行鲁棒训练。我们的方法可以灵活地结合使用,并使现有方法稳健。在共同的基准数据集上,我们表明芦荟大大提高了最新的ood检测的稳健性,对CiFar-10和46.59%的CiFar-100改善了58.4%的Auroc改善。
translated by 谷歌翻译
在过去的几十年中,人工智能的兴起使我们有能力解决日常生活中最具挑战性的问题,例如癌症的预测和自主航行。但是,如果不保护对抗性攻击,这些应用程序可能不会可靠。此外,最近的作品表明,某些对抗性示例可以在不同的模型中转移。因此,至关重要的是避免通过抵抗对抗性操纵的强大模型进行这种可传递性。在本文中,我们提出了一种基于特征随机化的方法,该方法抵抗了八次针对测试阶段深度学习模型的对抗性攻击。我们的新方法包括改变目标网络分类器中的训练策略并选择随机特征样本。我们认为攻击者具有有限的知识和半知识条件,以进行最普遍的对抗性攻击。我们使用包括现实和合成攻击的众所周知的UNSW-NB15数据集评估了方法的鲁棒性。之后,我们证明我们的策略优于现有的最新方法,例如最强大的攻击,包括针对特定的对抗性攻击进行微调网络模型。最后,我们的实验结果表明,我们的方法可以确保目标网络并抵抗对抗性攻击的转移性超过60%。
translated by 谷歌翻译
Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier. We obtain the class conditional Gaussian distributions with respect to (low-and upper-level) features of the deep models under Gaussian discriminant analysis, which result in a confidence score based on the Mahalanobis distance. While most prior methods have been evaluated for detecting either out-of-distribution or adversarial samples, but not both, the proposed method achieves the state-of-the-art performances for both cases in our experiments. Moreover, we found that our proposed method is more robust in harsh cases, e.g., when the training dataset has noisy labels or small number of samples. Finally, we show that the proposed method enjoys broader usage by applying it to class-incremental learning: whenever out-of-distribution samples are detected, our classification rule can incorporate new classes well without further training deep models.
translated by 谷歌翻译