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。

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.

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.

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.

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。

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.

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.

The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result-for example, how sensitive a prediction of zebra is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial perturbations are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.

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.

越来越多的电子健康记录（EHR）数据和深度学习技术进步的越来越多的可用性（DL）已经引发了在开发基于DL的诊断，预后和治疗的DL临床决策支持系统中的研究兴趣激增。尽管承认医疗保健的深度学习的价值，但由于DL的黑匣子性质，实际医疗环境中进一步采用的障碍障碍仍然存在。因此，有一个可解释的DL的新兴需求，它允许最终用户评估模型决策，以便在采用行动之前知道是否接受或拒绝预测和建议。在这篇综述中，我们专注于DL模型在医疗保健中的可解释性。我们首先引入深入解释性的方法，并作为该领域的未来研究人员或临床从业者的方法参考。除了这些方法的细节之外，我们还包括对这些方法的优缺点以及它们中的每个场景都适合的讨论，因此感兴趣的读者可以知道如何比较和选择它们供使用。此外，我们讨论了这些方法，最初用于解决一般域问题，已经适应并应用于医疗保健问题以及如何帮助医生更好地理解这些数据驱动技术。总的来说，我们希望这项调查可以帮助研究人员和从业者在人工智能（AI）和临床领域了解我们为提高其DL模型的可解释性并相应地选择最佳方法。

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

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 methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given task, interpretation models have become a crucial component in developing deep learning-based systems. Interpretation models enable the understanding of the inner workings of deep learning models and offer a sense of security in detecting the misuse of artifacts in the input data. Similar to prediction models, interpretation models are also susceptible to adversarial inputs. This work introduces two attacks, AdvEdge and AdvEdge$^{+}$, that deceive both the target deep learning model and the coupled interpretation model. We assess the effectiveness of proposed attacks against two deep learning model architectures coupled with four interpretation models that represent different categories of interpretation models. Our experiments include the attack implementation using various attack frameworks. We also explore the potential countermeasures against such attacks. Our analysis shows the effectiveness of our attacks in terms of deceiving the deep learning models and their interpreters, and highlights insights to improve and circumvent the attacks.

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。

对抗性实例的有趣现象引起了机器学习中的显着关注，对社区可能更令人惊讶的是存在普遍对抗扰动（UAPS），即欺骗目标DNN的单一扰动。随着对深层分类器的关注，本调查总结了最近普遍对抗攻击的进展，讨论了攻击和防御方的挑战，以及uap存在的原因。我们的目标是将此工作扩展为动态调查，该调查将定期更新其内容，以遵循关于在广泛的域中的UAP或通用攻击的新作品，例如图像，音频，视频，文本等。将讨论相关更新：https://bit.ly/2sbqlgg。我们欢迎未来的作者在该领域的作品，联系我们，包括您的新发现。

深层神经网络以其对各种机器学习和人工智能任务的精湛处理而闻名。但是，由于其过度参数化的黑盒性质，通常很难理解深层模型的预测结果。近年来，已经提出了许多解释工具来解释或揭示模型如何做出决策。在本文中，我们回顾了这一研究，并尝试进行全面的调查。具体来说，我们首先介绍并阐明了人们通常会感到困惑的两个基本概念 - 解释和解释性。为了解决解释中的研究工作，我们通过提出新的分类法来阐述许多解释算法的设计。然后，为了了解解释结果，我们还调查了评估解释算法的性能指标。此外，我们总结了使用“可信赖”解释算法评估模型的解释性的当前工作。最后，我们审查并讨论了深层模型的解释与其他因素之间的联系，例如对抗性鲁棒性和从解释中学习，并介绍了一些开源库，以解释算法和评估方法。

Vertical federated learning (VFL) is an emerging paradigm that enables collaborators to build machine learning models together in a distributed fashion. In general, these parties have a group of users in common but own different features. Existing VFL frameworks use cryptographic techniques to provide data privacy and security guarantees, leading to a line of works studying computing efficiency and fast implementation. However, the security of VFL's model remains underexplored.

Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational overhead in the process of attack. On the other hand, attacks with restricted perturbations are ineffective against defenses such as denoising or adversarial training. In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system. StyleFool first utilizes color theme proximity to select the best style image, which helps avoid unnatural details in the stylized videos. Meanwhile, the target class confidence is additionally considered in targeted attacks to influence the output distribution of the classifier by moving the stylized video closer to or even across the decision boundary. A gradient-free method is then employed to further optimize the adversarial perturbations. We carry out extensive experiments to evaluate StyleFool on two standard datasets, UCF-101 and HMDB-51. The experimental results demonstrate that StyleFool outperforms the state-of-the-art adversarial attacks in terms of both the number of queries and the robustness against existing defenses. Moreover, 50% of the stylized videos in untargeted attacks do not need any query since they can already fool the video classification model. Furthermore, we evaluate the indistinguishability through a user study to show that the adversarial samples of StyleFool look imperceptible to human eyes, despite unrestricted perturbations.

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。