Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and financial analysis have raised concerns regarding their reliability and trustworthiness. As automated systems become more mainstream, it is important their decisions be transparent, reliable and understandable by humans for better trust and confidence. To this effect, concept-based models such as Concept Bottleneck Models (CBMs) and Self-Explaining Neural Networks (SENN) have been proposed which constrain the latent space of a model to represent high level concepts easily understood by domain experts in the field. Although concept-based models promise a good approach to both increasing explainability and reliability, it is yet to be shown if they demonstrate robustness and output consistent concepts under systematic perturbations to their inputs. To better understand performance of concept-based models on curated malicious samples, in this paper, we aim to study their robustness to adversarial perturbations, which are also known as the imperceptible changes to the input data that are crafted by an attacker to fool a well-learned concept-based model. Specifically, we first propose and analyze different malicious attacks to evaluate the security vulnerability of concept based models. Subsequently, we propose a potential general adversarial training-based defense mechanism to increase robustness of these systems to the proposed malicious attacks. Extensive experiments on one synthetic and two real-world datasets demonstrate the effectiveness of the proposed attacks and the defense approach.

Explainability has been widely stated as a cornerstone of the responsible and trustworthy use of machine learning models. With the ubiquitous use of Deep Neural Network (DNN) models expanding to risk-sensitive and safety-critical domains, many methods have been proposed to explain the decisions of these models. Recent years have also seen concerted efforts that have shown how such explanations can be distorted (attacked) by minor input perturbations. While there have been many surveys that review explainability methods themselves, there has been no effort hitherto to assimilate the different methods and metrics proposed to study the robustness of explanations of DNN models. In this work, we present a comprehensive survey of methods that study, understand, attack, and defend explanations of DNN models. We also present a detailed review of different metrics used to evaluate explanation methods, as well as describe attributional attack and defense methods. We conclude with lessons and take-aways for the community towards ensuring robust explanations of DNN model predictions.

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.

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.

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。

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern on the robustness to adversarial examples, especially for security-critical tasks such as traffic sign identification for autonomous driving. Studies have unveiled the vulnerability of a well-trained DNN by demonstrating the ability of generating barely noticeable (to both human and machines) adversarial images that lead to misclassification. Furthermore, researchers have shown that these adversarial images are highly transferable by simply training and attacking a substitute model built upon the target model, known as a black-box attack to DNNs.Similar to the setting of training substitute models, in this paper we propose an effective black-box attack that also only has access to the input (images) and the output (confidence scores) of a targeted DNN. However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating adversarial examples. We use zeroth order stochastic coordinate descent along with dimension reduction, hierarchical attack and importance sampling techniques to * Pin-Yu Chen and Huan Zhang contribute equally to this work.

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.

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.

深度神经网络容易受到来自对抗性投入的攻击，并且最近，特洛伊木马误解或劫持模型的决定。我们通过探索有界抗逆性示例空间和生成的对抗网络内的自然输入空间来揭示有界面的对抗性实例 - 通用自然主义侵害贴片的兴趣类 - 我们呼叫TNT。现在，一个对手可以用一个自然主义的补丁来手臂自己，不太恶意，身体上可实现，高效 - 实现高攻击成功率和普遍性。 TNT是普遍的，因为在场景中的TNT中捕获的任何输入图像都将：i）误导网络（未确定的攻击）;或ii）迫使网络进行恶意决定（有针对性的攻击）。现在，有趣的是，一个对抗性补丁攻击者有可能发挥更大的控制水平 - 选择一个独立，自然的贴片的能力，与被限制为嘈杂的扰动的触发器 - 到目前为止只有可能与特洛伊木马攻击方法有可能干扰模型建设过程，以嵌入风险发现的后门;但是，仍然意识到在物理世界中部署的补丁。通过对大型视觉分类任务的广泛实验，想象成在其整个验证集50,000张图像中进行评估，我们展示了TNT的现实威胁和攻击的稳健性。我们展示了攻击的概括，以创建比现有最先进的方法实现更高攻击成功率的补丁。我们的结果表明，攻击对不同的视觉分类任务（CIFAR-10，GTSRB，PUBFIG）和多个最先进的深神经网络，如WieredEnet50，Inception-V3和VGG-16。

In order for machine learning to be trusted in many applications, it is critical to be able to reliably explain why the machine learning algorithm makes certain predictions. For this reason, a variety of methods have been developed recently to interpret neural network predictions by providing, for example, feature importance maps. For both scientific robustness and security reasons, it is important to know to what extent can the interpretations be altered by small systematic perturbations to the input data, which might be generated by adversaries or by measurement biases. In this paper, we demonstrate how to generate adversarial perturbations that produce perceptively indistinguishable inputs that are assigned the same predicted label, yet have very different interpretations. We systematically characterize the robustness of interpretations generated by several widely-used feature importance interpretation methods (feature importance maps, integrated gradients, and DeepLIFT) on ImageNet and CIFAR-10. In all cases, our experiments show that systematic perturbations can lead to dramatically different interpretations without changing the label. We extend these results to show that interpretations based on exemplars (e.g. influence functions) are similarly susceptible to adversarial attack. Our analysis of the geometry of the Hessian matrix gives insight on why robustness is a general challenge to current interpretation approaches.

已知深度神经网络（DNN）容易受到用不可察觉的扰动制作的对抗性示例的影响，即，输入图像的微小变化会引起错误的分类，从而威胁着基于深度学习的部署系统的可靠性。经常采用对抗训练（AT）来通过训练损坏和干净的数据的混合物来提高DNN的鲁棒性。但是，大多数基于AT的方法在处理\ textit {转移的对抗示例}方面是无效的，这些方法是生成以欺骗各种防御模型的生成的，因此无法满足现实情况下提出的概括要求。此外，对抗性训练一般的国防模型不能对具有扰动的输入产生可解释的预测，而不同的领域专家则需要一个高度可解释的强大模型才能了解DNN的行为。在这项工作中，我们提出了一种基于Jacobian规范和选择性输入梯度正则化（J-SIGR）的方法，该方法通过Jacobian归一化提出了线性化的鲁棒性，还将基于扰动的显着性图正规化，以模仿模型的可解释预测。因此，我们既可以提高DNN的防御能力和高解释性。最后，我们评估了跨不同体系结构的方法，以针对强大的对抗性攻击。实验表明，提出的J-Sigr赋予了针对转移的对抗攻击的鲁棒性，我们还表明，来自神经网络的预测易于解释。

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。

Gradient-based explanation is the cornerstone of explainable deep networks, but it has been shown to be vulnerable to adversarial attacks. However, existing works measure the explanation robustness based on $\ell_p$-norm, which can be counter-intuitive to humans, who only pay attention to the top few salient features. We propose explanation ranking thickness as a more suitable explanation robustness metric. We then present a new practical adversarial attacking goal for manipulating explanation rankings. To mitigate the ranking-based attacks while maintaining computational feasibility, we derive surrogate bounds of the thickness that involve expensive sampling and integration. We use a multi-objective approach to analyze the convergence of a gradient-based attack to confirm that the explanation robustness can be measured by the thickness metric. We conduct experiments on various network architectures and diverse datasets to prove the superiority of the proposed methods, while the widely accepted Hessian-based curvature smoothing approaches are not as robust as our method.

模型解释性的方法对于测试深度学习的公平性和健全性变得越来越重要。基于概念的可解释性技术使用了一系列人类解剖概念典范，以衡量概念对模型的内部输入表示的影响，这是这一研究中的重要线索。在这项工作中，我们表明，这些解释性方法可能会遭受对抗攻击的脆弱性，与他们要分析的模型相同。我们在两种著名的基于概念的可解释性方法上证明了这种现象：TCAV和刻面特征可视化。我们表明，通过仔细扰动正在研究的概念的示例，我们可以从根本上更改可解释性方法的输出。我们提出的攻击可以诱导积极的解释（对斑马进行分类时，圆点是模型的重要概念）或负面解释（条纹不是识别斑马图像的重要因素）。我们的工作强调了这样一个事实，即在安全至关重要的应用中，不仅需要机器学习管道，而且需要模型解释过程。

解释性对于理解深神经网络（DNN）的内部工作至关重要，并且许多解释方法产生显着图，这些图突出了输入图像的一部分，这些图像对DNN的预测有了最大的影响。在本文中，我们设计了一种后门攻击，该攻击改变了网络为输入图像而改变的显着图，仅带有注入的触发器，而肉眼看不见，同时保持预测准确性。该攻击依赖于将中毒的数据注入训练数据集中。显着性图被合并到用于训练深层模型的目标函数的惩罚项中，其对模型训练的影响基于触发器的存在。我们设计了两种类型的攻击：有针对性的攻击，该攻击可以实施显着性图的特定修改和无靶向攻击的特定攻击，而当原始显着性图的顶部像素的重要性得分大大降低时。我们对针对各种深度学习体系结构的基于梯度和无梯度解释方法进行的后门攻击进行经验评估。我们表明，在部署不信任来源开发的深度学习模型时，我们的攻击构成了严重的安全威胁。最后，在补充中，我们证明了所提出的方法可以在倒置的设置中使用，在这种情况下，只有在存在触发器的情况下才能获得正确的显着性图（键），从而有效地使解释系统仅适用于选定的用户。

我们从频道明智激活的角度调查CNN的对抗性鲁棒性。通过比较\ Textit {非鲁棒}（通常训练）和\ exingit {REXITIT {REARUSTIFIED}（普及培训的）模型，我们观察到对抗性培训（AT）通过将频道明智的数据与自然的渠道和自然的对抗激活对齐来强调CNN同行。然而，在处理逆势数据时仍仍会过度激活以\ texit {excy-computive}（nr）的频道仍会过度激活。此外，我们还观察到，在所有课程上不会导致类似的稳健性。对于强大的类，具有较大激活大小的频道通常是更长的\ extedit {正相关}（pr）到预测，但这种对齐不适用于非鲁棒类。鉴于这些观察结果，我们假设抑制NR通道并对齐PR与其相关性进一步增强了在其下的CNN的鲁棒性。为了检查这个假设，我们介绍了一种新的机制，即\下划线{C} Hannel-Wise \ Underline {i} Mportance的\下划线{F} eature \ Underline {s}选举（CIFS）。 CIFS通过基于与预测的相关性产生非负乘法器来操纵某些层的激活。在包括CIFAR10和SVHN的基准数据集上的广泛实验明确验证了强制性CNN的假设和CIFS的有效性。 \ url {https://github.com/hanshuyan/cifs}

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x that is similar to x but classified as t. This makes it difficult to apply neural networks in security-critical areas. Defensive distillation is a recently proposed approach that can take an arbitrary neural network, and increase its robustness, reducing the success rate of current attacks' ability to find adversarial examples from 95% to 0.5%.In this paper, we demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability. Our attacks are tailored to three distance metrics used previously in the literature, and when compared to previous adversarial example generation algorithms, our attacks are often much more effective (and never worse). Furthermore, we propose using high-confidence adversarial examples in a simple transferability test we show can also be used to break defensive distillation. We hope our attacks will be used as a benchmark in future defense attempts to create neural networks that resist adversarial examples.

有针对性的训练集攻击将恶意实例注入训练集中，以导致训练有素的模型错误地标记一个或多个特定的测试实例。这项工作提出了目标识别的任务，该任务决定了特定的测试实例是否是训练集攻击的目标。目标识别可以与对抗性识别相结合，以查找（并删除）攻击实例，从而减轻对其他预测的影响，从而减轻攻击。我们没有专注于单个攻击方法或数据模式，而是基于影响力估计，这量化了每个培训实例对模型预测的贡献。我们表明，现有的影响估计量的不良实际表现通常来自于他们对训练实例和迭代次数的过度依赖。我们重新归一化的影响估计器解决了这一弱点。他们的表现远远超过了原始估计量，可以在对抗和非对抗环境中识别有影响力的训练示例群体，甚至发现多达100％的对抗训练实例，没有清洁数据误报。然后，目标识别简化以检测具有异常影响值的测试实例。我们证明了我们的方法对各种数据域的后门和中毒攻击的有效性，包括文本，视觉和语音，以及针对灰色盒子的自适应攻击者，该攻击者专门优化了逃避我们方法的对抗性实例。我们的源代码可在https://github.com/zaydh/target_indistification中找到。

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the training dataset such that the impact on the model's predictions is minimal. The adversary subsequently triggers a request to remove a subset of the introduced points at which point the attack is unleashed and the model's predictions are negatively affected. In particular, we consider clean-label targeted attacks (in which the goal is to cause the model to misclassify a specific test point) on datasets including CIFAR-10, Imagenette, and Imagewoof. This attack is realized by constructing camouflage datapoints that mask the effect of a poisoned dataset.

Although Deep Neural Networks (DNNs) have achieved impressive results in computer vision, their exposed vulnerability to adversarial attacks remains a serious concern. A series of works has shown that by adding elaborate perturbations to images, DNNs could have catastrophic degradation in performance metrics. And this phenomenon does not only exist in the digital space but also in the physical space. Therefore, estimating the security of these DNNs-based systems is critical for safely deploying them in the real world, especially for security-critical applications, e.g., autonomous cars, video surveillance, and medical diagnosis. In this paper, we focus on physical adversarial attacks and provide a comprehensive survey of over 150 existing papers. We first clarify the concept of the physical adversarial attack and analyze its characteristics. Then, we define the adversarial medium, essential to perform attacks in the physical world. Next, we present the physical adversarial attack methods in task order: classification, detection, and re-identification, and introduce their performance in solving the trilemma: effectiveness, stealthiness, and robustness. In the end, we discuss the current challenges and potential future directions.