几年的研究表明,在理论和实践中,机器学习系统容易受到对抗的例子。到目前为止,这种攻击主要有针对性的视觉模型,利用人类和机器感知之间的差距。虽然基于文本的模型也被对抗例子遭到攻击,但这种攻击努力保持语义意义和无法区分。在本文中,我们探讨了大类的对抗示例,可用于在黑盒设置中攻击基于文本的模型,而不会对输入进行任何人类可知的视觉修改。我们使用对人眼不可察觉的编码特异性扰动来操纵从神经计算机翻译管道到网络搜索引擎的各种自然语言处理(NLP)系统的输出。我们发现,通过单一的难以察觉的编码注射 - 代表一个无形的字符,同型角色,重新排序或删除 - 攻击者可以显着降低易受伤害的模型的性能,并且三次注射大多数型号可以在功能上打破。除了由Facebook,IBM和HuggingFace发布的开源模型之外,我们攻击目前部署的商业系统这一新颖的一系列攻击对许多语言处理系统提供了重大威胁:攻击者可以以目标方式影响系统而没有任何关于底层模型的假设。我们得出结论,基于文本的NLP系统需要仔细的输入消毒,就像传统应用程序一样,并且考虑到这样的系统现在正在迅速地部署,需要建筑师和运营商的紧急注意。
translated by 谷歌翻译
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。
translated by 谷歌翻译
数据增强是自然语言处理(NLP)模型的鲁棒性评估的重要组成部分,以及增强他们培训的数据的多样性。在本文中,我们呈现NL-Cogmenter,这是一种新的参与式Python的自然语言增强框架,它支持创建两个转换(对数据的修改)和过滤器(根据特定功能的数据拆分)。我们描述了框架和初始的117个变换和23个过滤器,用于各种自然语言任务。我们通过使用其几个转换来分析流行自然语言模型的鲁棒性来证明NL-Upmenter的功效。基础架构,Datacards和稳健性分析结果在NL-Augmenter存储库上公开可用(\ url {https://github.com/gem-benchmark/nl-augmenter})。
translated by 谷歌翻译
现在,错误和虚假信息已成为我们安全和安全的全球威胁。为了应对在线错误信息的规模,一个可行的解决方案是通过检索和验证相关证据来自动对索赔进行事实检查。尽管在推动自动事实验证方面取得了最新进展,但仍缺乏对可能针对此类系统的攻击向量的全面评估。特别是,自动化事实验证过程可能容易受到其试图打击的确切虚假信息。在这项工作中,我们假设一个对手可以自动使用在线证据擦洗,以通过伪装相关证据或种植误导性的证据来破坏事实检查模型。我们首先提出了探索性分类法,该分类法涵盖了这两个目标和不同的威胁模型维度。在此指导下,我们设计并提出了几种潜在的攻击方法。我们表明,除了产生多样化和索赔一致的证据之外,还可以在证据中巧妙地修改索赔空位段。结果,我们在分类法的许多不同排列中高度降低了事实检查的表现。这些攻击也对索赔后的事后修改也很强大。我们的分析进一步暗示了在面对矛盾的证据时,模型推断的潜在局限性。我们强调,这些攻击可能会对此类模型的可检查和人类使用情况产生有害的影响,我们通过讨论未来防御的挑战和方向来得出结论。
translated by 谷歌翻译
Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simple tactics to subvert ML-driven systems, and as a result security practitioners have not prioritized adversarial ML defenses. Motivated by the apparent gap between researchers and practitioners, this position paper aims to bridge the two domains. We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next we analyze all adversarial ML papers recently published in top security conferences, highlighting positive trends and blind spots. Finally, we state positions on precise and cost-driven threat modeling, collaboration between industry and academia, and reproducible research. We believe that our positions, if adopted, will increase the real-world impact of future endeavours in adversarial ML, bringing both researchers and practitioners closer to their shared goal of improving the security of ML systems.
translated by 谷歌翻译
基于文本的对抗攻击变得越来越普遍,通用互联网用户可以访问。随着这些攻击的繁殖,解决模型鲁棒性中差距的需求即将变得迫在眉睫。在对抗数据上进行重新培训可能会提高性能,但这些模型在该模型中仍有一类其他角色级攻击。此外,重新培训模型的过程是时间和资源密集型,创造了对轻巧,可重复使用的防御的需求。在这项工作中,我们提出了对抗性文本标准器,这是一种新颖的方法,可恢复具有低计算开销的攻击内容上的基线性能。我们评估了标准级化合物在容易发生攻击的两个问题领域的功效,即仇恨言论和自然语言推断。我们发现,文本归一化提供了针对角色级攻击的任务不足的防御,该攻击可以对对抗性再培训解决方案进行补充,这更适合语义改变。
translated by 谷歌翻译
关于NLP模型的最先进攻击缺乏对成功攻击的共享定义。我们将思考从过去的工作蒸馏成统一的框架:一个成功的自然语言对抗性示例是欺骗模型并遵循一些语言限制的扰动。然后,我们分析了两个最先进的同义词替换攻击的产出。我们发现他们的扰动通常不会保留语义,38%引入语法错误。人类调查显示,为了成功保留语义,我们需要大大增加交换词语的嵌入和原始和扰动句子的句子编码之间的最小余弦相似之处。与更好的保留语义和语法性,攻击成功率下降超过70个百分点。
translated by 谷歌翻译
Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning based NER models are increasingly being applied in privacy-sensitive applications that need automatic and scalable identification of sensitive information to redact text for data sharing. In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training datasets. With updated pre-trained NER models from spaCy, we demonstrate two distinct membership attacks on these models. Our first attack capitalizes on unintended memorization in the NER's underlying neural network, a phenomenon NNs are known to be vulnerable to. Our second attack leverages a timing side-channel to target NER models that maintain vocabularies constructed from the training data. We show that different functional paths of words within the training dataset in contrast to words not previously seen have measurable differences in execution time. Revealing membership status of training samples has clear privacy implications, e.g., in text redaction, sensitive words or phrases to be found and removed, are at risk of being detected in the training dataset. Our experimental evaluation includes the redaction of both password and health data, presenting both security risks and privacy/regulatory issues. This is exacerbated by results that show memorization with only a single phrase. We achieved 70% AUC in our first attack on a text redaction use-case. We also show overwhelming success in the timing attack with 99.23% AUC. Finally we discuss potential mitigation approaches to realize the safe use of NER models in light of the privacy and security implications of membership inference attacks.
translated by 谷歌翻译
在过去的几年中,保护NLP模型免受拼写错误的障碍是研究兴趣的对象。现有的补救措施通常会损害准确性,或者需要对每个新的攻击类别进行完整的模型重新训练。我们提出了一种新颖的方法,可以向基于变压器的NLP模型中的拼写错误增加弹性。可以实现这种鲁棒性,而无需重新训练原始的NLP模型,并且只有最小的语言丧失理解在没有拼写错误的输入上的性能。此外,我们提出了一种新的有效近似方法来产生对抗性拼写错误,这大大降低了评估模型对对抗性攻击的弹性所需的成本。
translated by 谷歌翻译
我们调查对神经序列到序列(SEQ2SEQ)模型的新威胁:训练时间攻击使模型“自旋”的输出,以支持对抗的选择情绪或观点,但仅在输入包含时逆境触发词。例如,旋转的摘要模型将输出提到某些个人或组织名称的文本的正摘要。模型纺纱使得宣传的AS-A-Service。对手可以创建为所选触发产生所需的旋转的自定义语言模型,然后部署它们以生成虚假信息(平台攻击),或者将它们注入ML培训管道(供应链攻击),将恶意功能转移到下游模型。在技​​术术语中,模型纺纱将一个“Meta-Backdoor”引入模型中。虽然传统的后门导致模型在具有触发器的输入上产生不正确的输出,但旋转模型的输出保留上下文并维持标准精度度量,但也满足了对手(例如,积极情绪)选择的元任务。为了证明模型纺丝的可行性,我们开发了一种新的回溯技术。它将对手元任务堆叠到SEQ2SEQ模型上,将所需的元任务输出返回到嵌入空间中的所需的元任务输出,我们称之为“伪字”,并使用伪字来换档SEQ2Seq模型的整个输出分布。我们评估了对语言生成,摘要和翻译模型的攻击,具有不同的触发器和诸如情感,毒性和征集等方面的触发器和荟萃任务。旋转模型在满足对抗的元任务时保持其准确性指标。在供应链中攻击旋转转移到下游型号。最后,我们提出了一个黑匣子,元任务独立的防御,以检测选择性地将旋转旋转到具有特定触发的输入的模型。
translated by 谷歌翻译
如今,人们在网上平台上生成并分享大量内容(例如,社交网络,博客)。 2021年,每分钟为119亿日常积极的Facebook用户发布了大约15万张照片。内容主持人不断监控这些在线平台,以防止扩散不适当的内容(例如,讨厌语音,裸露图像)。基于深度学习(DL)的进步,自动内容主持人(ACM)帮助人类主持人处理高数据量。尽管他们的优势,攻击者可以利用DL组件的弱点(例如,预处理,模型)来影响其性能。因此,攻击者可以利用这些技术来通过逃避ACM来扩散不适当的内容。在这项工作中,我们提出了CAPTCHA攻击(CAPA),这是一种允许用户通过逃避ACM控件来扩散不恰当的文本的对抗技术。通过生成自定义文本CAPTCHAS的CAPA,利用ACM的粗心设计实现和内部程序漏洞。我们对现实世界ACM的攻击进行了测试,结果证实了我们简单但有效攻击的凶猛,在大多数情况下达到了100%的逃避成功。与此同时,我们展示了设计CAPA缓解,在CAPTCHAS研究区开辟了新挑战的困难。
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
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.
translated by 谷歌翻译
The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners that could benefit from such systems, like librarians or musicologists. The relevant topics of interest for the workshop include, but are not limited to: Music reading systems; Optical music recognition; Datasets and performance evaluation; Image processing on music scores; Writer identification; Authoring, editing, storing and presentation systems for music scores; Multi-modal systems; Novel input-methods for music to produce written music; Web-based Music Information Retrieval services; Applications and projects; Use-cases related to written music. These are the proceedings of the 2nd International Workshop on Reading Music Systems, held in Delft on the 2nd of November 2019.
translated by 谷歌翻译
恶意软件是跨越多个操作系统和各种文件格式的计算机的最损害威胁之一。为了防止不断增长的恶意软件的威胁,已经提出了巨大的努力来提出各种恶意软件检测方法,试图有效和有效地检测恶意软件。最近的研究表明,一方面,现有的ML和DL能够卓越地检测新出现和以前看不见的恶意软件。然而,另一方面,ML和DL模型本质上易于侵犯对抗性示例形式的对抗性攻击,这通过略微仔细地扰乱了合法输入来混淆目标模型来恶意地产生。基本上,在计算机视觉领域最初广泛地研究了对抗性攻击,并且一些快速扩展到其他域,包括NLP,语音识别甚至恶意软件检测。在本文中,我们专注于Windows操作系统系列中的便携式可执行文件(PE)文件格式的恶意软件,即Windows PE恶意软件,作为在这种对抗设置中研究对抗性攻击方法的代表性案例。具体而言,我们首先首先概述基于ML / DL的Windows PE恶意软件检测的一般学习框架,随后突出了在PE恶意软件的上下文中执行对抗性攻击的三个独特挑战。然后,我们进行全面和系统的审查,以对PE恶意软件检测以及增加PE恶意软件检测的稳健性的相应防御,对近最新的对手攻击进行分类。我们首先向Windows PE恶意软件检测的其他相关攻击结束除了对抗对抗攻击之外,然后对未来的研究方向和机遇脱落。
translated by 谷歌翻译
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.
translated by 谷歌翻译
评论是源代码的重要组成部分,是文档的主要来源。这引起了人们对使用大量注释的兴趣训练或评估消耗或生产它们的工具,例如生成甲骨文,甚至是从注释中生成代码,或自动生成代码摘要。这项工作大部分对评论的结构和质量做出了强烈的假设,例如假设它们主要由适当的英语句子组成。但是,我们对这些用例的现有评论的实际质量知之甚少。评论通常包含在其他类型的文本中看不到的独特结构和元素,并且从中过滤或提取信息需要额外的谨慎。本文探讨了来自GitHub的840个最受欢迎的开源项目和Srilab数据集的8422个项目的Python评论的内容和质量,并且Na \“ Ive vs.深入过滤的影响都可以使用现有注释来用于使用现有注释。培训和评估产生评论的系统。
translated by 谷歌翻译
机器学习算法已被证明通过系统修改(例如,图像识别)中的输入(例如,对抗性示例)的系统修改(例如,对抗性示例)容易受到对抗操作的影响。在默认威胁模型下,对手利用了图像的无约束性质。每个功能(像素)完全由对手控制。但是,尚不清楚这些攻击如何转化为限制对手可以修改的特征以及如何修改特征的约束域(例如,网络入侵检测)。在本文中,我们探讨了受约束的域是否比不受约束的域对对抗性示例生成算法不那么脆弱。我们创建了一种用于生成对抗草图的算法:针对性的通用扰动向量,该向量在域约束的信封内编码特征显着性。为了评估这些算法的性能,我们在受约束(例如网络入侵检测)和不受约束(例如图像识别)域中评估它们。结果表明,我们的方法在约束域中产生错误分类率,这些域与不受约束的域(大于95%)相当。我们的调查表明,受约束域暴露的狭窄攻击表面仍然足够大,可以制作成功的对抗性例子。因此,约束似乎并不能使域变得健壮。实际上,只有五个随机选择的功能,仍然可以生成对抗性示例。
translated by 谷歌翻译
我们想要模型的文本单位是什么?从字节到多字表达式,可以在许多粒度下分析和生成文本。直到最近,大多数自然语言处理(NLP)模型通过单词操作,将那些作为离散和原子令牌处理,但从字节对编码(BPE)开始,基于次字的方法在许多领域都变得占主导地位,使得仍然存在小词汇表允许快速推断。是道路字符级模型的结束或字节级处理吗?在这项调查中,我们通过展示和评估基于学习分割的词语和字符以及基于子字的方法的混合方法以及基于学习的分割的杂交方法,连接多行工作。我们得出结论,对于所有应用来说,并且可能永远不会成为所有应用的银子弹奇异解决方案,并且严重思考令牌化对许多应用仍然很重要。
translated by 谷歌翻译
文本指导的图像生成模型,例如DALL-E 2和稳定的扩散,最近受到了学术界和公众的关注。这些模型提供了文本描述,能够生成描绘各种概念和样式的高质量图像。但是,此类模型接受了大量公共数据的培训,并从其培训数据中隐含地学习关系,这些数据并不明显。我们证明,可以通过简单地用视觉上类似的非拉丁字符替换文本描述中的单个字符来触发并注入生成的图像中的常见多模型模型,这些偏见可以被触发并注入生成的图像。这些所谓的同符文更换使恶意用户或服务提供商能够诱导偏见到生成的图像中,甚至使整个一代流程变得无用。我们实际上说明了对DALL-E 2和稳定扩散的这种攻击,例如文本引导的图像生成模型,并进一步表明夹子的行为也相似。我们的结果进一步表明,经过多语言数据训练的文本编码器提供了一种减轻同符替代效果的方法。
translated by 谷歌翻译