Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold conjecture has inspired a novel line of defenses against adversarial attacks on images. In this study, we find a similar phenomenon occurs in the contextualized embedding space induced by pretrained language models, in which adversarial texts tend to have their embeddings diverge from the manifold of natural ones. Based on this finding, we propose Textual Manifold-based Defense (TMD), a defense mechanism that projects text embeddings onto an approximated embedding manifold before classification. It reduces the complexity of potential adversarial examples, which ultimately enhances the robustness of the protected model. Through extensive experiments, our method consistently and significantly outperforms previous defenses under various attack settings without trading off clean accuracy. To the best of our knowledge, this is the first NLP defense that leverages the manifold structure against adversarial attacks. Our code is available at \url{https://github.com/dangne/tmd}.

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP). However, in contrast to the computer vision domain where the first-order projected gradient descent (PGD) is used as the benchmark approach to generate adversarial examples for robustness evaluation, there lacks a principled first-order gradient-based robustness evaluation framework in NLP. The emerging optimization challenges lie in 1) the discrete nature of textual inputs together with the strong coupling between the perturbation location and the actual content, and 2) the additional constraint that the perturbed text should be fluent and achieve a low perplexity under a language model. These challenges make the development of PGD-like NLP attacks difficult. To bridge the gap, we propose TextGrad, a new attack generator using gradient-driven optimization, supporting high-accuracy and high-quality assessment of adversarial robustness in NLP. Specifically, we address the aforementioned challenges in a unified optimization framework. And we develop an effective convex relaxation method to co-optimize the continuously-relaxed site selection and perturbation variables and leverage an effective sampling method to establish an accurate mapping from the continuous optimization variables to the discrete textual perturbations. Moreover, as a first-order attack generation method, TextGrad can be baked into adversarial training to further improve the robustness of NLP models. Extensive experiments are provided to demonstrate the effectiveness of TextGrad not only in attack generation for robustness evaluation but also in adversarial defense.

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。

尽管在许多机器学习任务方面取得了巨大成功，但深度神经网络仍然易于对抗对抗样本。虽然基于梯度的对抗攻击方法在计算机视野领域探索，但由于文本的离散性质，直接应用于自然语言处理中，这是不切实际的。为了弥合这一差距，我们提出了一般框架，以适应现有的基于梯度的方法来制作文本对抗性样本。在该框架中，将基于梯度的连续扰动添加到嵌入层中，并在前向传播过程中被放大。然后用掩模语言模型头解码最终的扰动潜在表示以获得潜在的对抗性样本。在本文中，我们将我们的框架与\ textbf {t} Extual \ TextBF {P} ROJECTED \ TextBF {G} Radient \ TextBF {D} excent（\ TextBF {TPGD}）进行ronject \ textbf {p}。我们通过在三个基准数据集上执行转移黑匣子攻击来评估我们的框架来评估我们的框架。实验结果表明，与强基线方法相比，我们的方法达到了更好的性能，并产生更精细和语法的对抗性样本。所有代码和数据都将公开。

我们将自然语言处理模型的脆弱性归因于以下事实：类似的输入转换为嵌入空间中不同的表示形式，导致输出不一致，我们提出了一种新颖的强大训练方法，称为快速三胞胎度量度量学习（FTML）。具体而言，我们认为原始样本应具有相似的表示及其对手对应物，并将其代表与其他样品区分开，以提高鲁棒性。为此，我们将三胞胎度量学习采用标准培训中，以将单词更接近其正样本（即同义词），并在嵌入空间中推出其负面样本（即非综合样品）。广泛的实验表明，FTML可以显着促进模型的鲁棒性，以针对各种高级对抗攻击，同时保持对原始样品的竞争性分类精度。此外，我们的方法是有效的，因为它只需要调整嵌入方式，并且在标准培训上引入了很少的开销。我们的工作显示出通过稳健的单词嵌入来改善文本鲁棒性的巨大潜力。

基于深度学习的NLP模型被发现容易受到Word替代扰动的影响。在他们被广泛采用之前，需要解决坚固性的基本问题。沿着这条线，我们提出了一个正式的框架来评估词语级鲁棒性。首先，要研究模型的安全区域，我们引入了稳健的半径，这是模型可以抵抗任何扰动的边界。计算最大鲁棒性半径的计算变硬，我们估计其上限和下限。我们将攻击方法作为寻求上限和设计伪动态编程算法的攻击方法，用于更紧密的上限。然后验证方法用于下限。此外，为了评估在安全半径之外的区域的稳健性，我们从另一个视图中重新征服鲁棒性：量化。引入了具有严格统计保障的鲁棒度量，以测量对抗性示例的定量，这表明该模型对安全半径之外的扰动的敏感性。该度量有助于我们弄清楚为什么伯特这样的最先进的模型可以很容易地被几个单词替换所吸引，但在现实世界的噪音存在下概括很好。

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can cause misclassification of legitimate images. We propose Defense-GAN, a new framework leveraging the expressive capability of generative models to defend deep neural networks against such attacks. Defense-GAN is trained to model the distribution of unperturbed images. At inference time, it finds a close output to a given image which does not contain the adversarial changes. This output is then fed to the classifier. Our proposed method can be used with any classification model and does not modify the classifier structure or training procedure. It can also be used as a defense against any attack as it does not assume knowledge of the process for generating the adversarial examples. We empirically show that Defense-GAN is consistently effective against different attack methods and improves on existing defense strategies. Our code has been made publicly available at https://github.com/kabkabm/defensegan.

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.

最近的作品表明了解释性和鲁棒性是值得信赖和可靠的文本分类的两个关键成分。然而，以前的作品通常是解决了两个方面的一个：i）如何提取准确的理由，以便在有利于预测的同时解释; ii）如何使预测模型对不同类型的对抗性攻击稳健。直观地，一种产生有用的解释的模型应该对对抗性攻击更加强大，因为我们无法信任输出解释的模型，而是在小扰动下改变其预测。为此，我们提出了一个名为-BMC的联合分类和理由提取模型。它包括两个关键机制：混合的对手训练（AT）旨在在离散和嵌入空间中使用各种扰动，以改善模型的鲁棒性，边界匹配约束（BMC）有助于利用边界信息的引导来定位理由。基准数据集的性能表明，所提出的AT-BMC优于分类和基本原子的基础，由大边距提取。鲁棒性分析表明，建议的AT-BMC将攻击成功率降低了高达69％。经验结果表明，强大的模型与更好的解释之间存在连接。

大多数对抗攻击防御方法依赖于混淆渐变。这些方法在捍卫基于梯度的攻击方面是成功的;然而，它们容易被攻击绕过，该攻击不使用梯度或近似近似和使用校正梯度的攻击。不存在不存在诸如对抗培训等梯度的防御，但这些方法通常对诸如其幅度的攻击进行假设。我们提出了一种分类模型，该模型不会混淆梯度，并且通过施工而强大而不承担任何关于攻击的知识。我们的方法将分类作为优化问题，我们“反转”在不受干扰的自然图像上培训的条件发电机，以找到生成最接近查询图像的类。我们假设潜在的脆性抗逆性攻击源是前馈分类器的高度低维性质，其允许对手发现输入空间中的小扰动，从而导致输出空间的大变化。另一方面，生成模型通常是低到高维的映射。虽然该方法与防御GaN相关，但在我们的模型中使用条件生成模型和反演而不是前馈分类是临界差异。与Defense-GaN不同，它被证明生成了容易规避的混淆渐变，我们表明我们的方法不会混淆梯度。我们展示了我们的模型对黑箱攻击的极其强劲，并与自然训练的前馈分类器相比，对白盒攻击的鲁棒性提高。

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimizationbased attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining noncertified white-box-secure defenses at ICLR 2018, we find obfuscated gradients are a common occurrence, with 7 of 9 defenses relying on obfuscated gradients. Our new attacks successfully circumvent 6 completely, and 1 partially, in the original threat model each paper considers.

我们专注于在黑框设置中对模型的对抗性攻击的问题，攻击者旨在制作对受害者模型的查询访问有限的对抗性示例。现有的黑框攻击主要基于贪婪的算法，使用预先计算的关键位置来扰动，从而严重限制了搜索空间，并可能导致次优的解决方案。为此，我们提出了使用贝叶斯优化的查询有效的黑盒攻击，该贝叶斯优化使用自动相关性确定（ARD）分类内核动态计算重要位置。我们引入了块分解和历史次采样技术，以提高输入序列长时间时贝叶斯优化的可伸缩性。此外，我们开发了一种优化后算法，该算法找到了具有较小扰动大小的对抗示例。关于自然语言和蛋白质分类任务的实验表明，与先前的最新方法相比，我们的方法始终达到更高的攻击成功率，查询计数和修改率的显着降低。

最近的自然语言处理（NLP）技术在基准数据集中实现了高性能，主要原因是由于深度学习性能的显着改善。研究界的进步导致了最先进的NLP任务的生产系统的巨大增强，例如虚拟助理，语音识别和情感分析。然而，随着对抗性攻击测试时，这种NLP系统仍然仍然失败。初始缺乏稳健性暴露于当前模型的语言理解能力中的令人不安的差距，当NLP系统部署在现实生活中时，会产生问题。在本文中，我们通过以各种维度的系统方式概述文献来展示了NLP稳健性研究的结构化概述。然后，我们深入了解稳健性的各种维度，跨技术，指标，嵌入和基准。最后，我们认为，鲁棒性应该是多维的，提供对当前研究的见解，确定文学中的差距，以建议值得追求这些差距的方向。

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.

数据增强是通过转换为机器学习的人工创建数据的人工创建，是一个跨机器学习学科的研究领域。尽管它对于增加模型的概括功能很有用，但它还可以解决许多其他挑战和问题，从克服有限的培训数据到正规化目标到限制用于保护隐私的数据的数量。基于对数据扩展的目标和应用的精确描述以及现有作品的分类法，该调查涉及用于文本分类的数据增强方法，并旨在为研究人员和从业者提供简洁而全面的概述。我们将100多种方法划分为12种不同的分组，并提供最先进的参考文献来阐述哪种方法可以通过将它们相互关联，从而阐述了哪种方法。最后，提供可能构成未来工作的基础的研究观点。

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

一项工作表明，自然文本处理模型容易受到对抗示例的影响。相应地，提出了各种辩护方法来减轻文本对抗性示例的威胁，例如对抗性训练，输入转换，检测等。在这项工作中，我们将基于同义词替代的基于同义词的文本对抗性攻击作为特定的单词序列对待优化过程替代品，每个单词相互影响其他单词。我们确定我们可以通过随机替换一个单词的同义词来消除这种相互作用并消除对抗性扰动。基于此观察，我们提出了一种新型的文本对抗示例检测方法，称为随机替代和投票（RS＆V），该方法通过累积通过与同步输入文本中随机替换单词生成的k样品的liogits来投票标签。提出的RS＆V通常适用于任何现有的神经网络，而无需修改体系结构或额外的培训，并且先前的工作使分类网络本身更强大是正交的。在三个基准数据集上进行的经验评估表明，与现有检测方法相比，我们的RS＆V可以更成功地检测到文本对抗示例，同时保持良性样本上的高分类精度。

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models. However, these tickets are proved to be notrobust to adversarial examples, and even worse than their PLM counterparts. To address this problem, we propose a novel method based on learning binary weight masks to identify robust tickets hidden in the original PLMs. Since the loss is not differentiable for the binary mask, we assign the hard concrete distribution to the masks and encourage their sparsity using a smoothing approximation of L0 regularization.Furthermore, we design an adversarial loss objective to guide the search for robust tickets and ensure that the tickets perform well bothin accuracy and robustness. Experimental results show the significant improvement of the proposed method over previous work on adversarial robustness evaluation.

NLP系统的Black-Box对抗攻击中最近的工作引起了很多关注。先前的黑框攻击假设攻击者可以根据选定的输入观察目标模型的输出标签。在这项工作中，受到对抗性转移性的启发，我们提出了一种新型的黑盒NLP对抗性攻击，攻击者可以选择相似的域并将对抗性示例转移到目标域并在目标模型中导致性能差。基于领域的适应理论，我们提出了一种称为Learn2Weight的防御策略，该策略训练以预测目标模型的重量调整，以防止对类似的对抗性示例的攻击。使用亚马逊多域情绪分类数据集，我们从经验上表明，与标准的黑盒防御方法（例如对抗性训练和防御性蒸馏）相比，Learn2Weight对攻击有效。这项工作有助于越来越多的有关机器学习安全的文献。

现有的研究表明，对抗性示例可以直接归因于具有高度预测性的非稳态特征的存在，但很容易被对手对愚弄NLP模型进行操纵。在这项研究中，我们探讨了捕获特定于任务的鲁棒特征的可行性，同时使用信息瓶颈理论消除了非舒适的特征。通过广泛的实验，我们表明，通过我们的信息基于瓶颈的方法训练的模型能够在稳健的精度上取得显着提高，超过了所有先前报道的防御方法的性能，而在SST-2上几乎没有遭受清洁准确性的表现下降，Agnews和IMDB数据集。