处理感官输入的机器学习系统的兴起使人与机器感知之间的比较有所增加。但是，这种比较面临着一个挑战：尽管机器对某些刺激的感知通常可以通过直接和明确的措施来探讨，但人类知识的大部分知识是潜在的，不完整的或不可用的。在这里，我们探讨了这种不对称性如何导致这种比较误解人类和机器感知的重叠。作为一个案例研究，我们考虑了人类对\ textit {对抗性语音}的感知 - 合成音频命令被自动语音识别系统识别为有效消息，但据报道，人类听众听到了无意义的噪音。在五个实验中，我们适应了人类心理物理学文献的任务设计，以表明即使受试者无法自由地抄写此类语音命令（以前的人类理解基准），他们也可以表现出其他形式的理解，包括从紧密匹配的对抗性语言中歧视对抗性演讲非语音（实验1--2），在对抗性语音（实验3--4）中开始完成的常见短语，并解决了对抗性语音中提出的简单数学问题（实验5） - 即使对于先前被描述为人类无法理解的刺激听众。我们建议在比较人类和机器感知时采用这种“敏感测试”，并讨论评估系统之间重叠的这种方法的更广泛的后果。

Deepfakes are computationally-created entities that falsely represent reality. They can take image, video, and audio modalities, and pose a threat to many areas of systems and societies, comprising a topic of interest to various aspects of cybersecurity and cybersafety. In 2020 a workshop consulting AI experts from academia, policing, government, the private sector, and state security agencies ranked deepfakes as the most serious AI threat. These experts noted that since fake material can propagate through many uncontrolled routes, changes in citizen behaviour may be the only effective defence. This study aims to assess human ability to identify image deepfakes of human faces (StyleGAN2:FFHQ) from nondeepfake images (FFHQ), and to assess the effectiveness of simple interventions intended to improve detection accuracy. Using an online survey, 280 participants were randomly allocated to one of four groups: a control group, and 3 assistance interventions. Each participant was shown a sequence of 20 images randomly selected from a pool of 50 deepfake and 50 real images of human faces. Participants were asked if each image was AI-generated or not, to report their confidence, and to describe the reasoning behind each response. Overall detection accuracy was only just above chance and none of the interventions significantly improved this. Participants' confidence in their answers was high and unrelated to accuracy. Assessing the results on a per-image basis reveals participants consistently found certain images harder to label correctly, but reported similarly high confidence regardless of the image. Thus, although participant accuracy was 62% overall, this accuracy across images ranged quite evenly between 85% and 30%, with an accuracy of below 50% for one in every five images. We interpret the findings as suggesting that there is a need for an urgent call to action to address this threat.

深度学习技术的发展极大地促进了自动语音识别（ASR）技术的性能提高，该技术证明了在许多任务中与人类听力相当的能力。语音接口正变得越来越广泛地用作许多应用程序和智能设备的输入。但是，现有的研究表明，DNN很容易受到轻微干扰的干扰，并且会出现错误的识别，这对于由声音控制的智能语音应用非常危险。

对抗商业黑匣子语音平台的对抗攻击，包括云语音API和语音控制设备，直到近年来接受了很少的关注。目前的“黑匣子”攻击所有严重依赖于预测/置信度评分的知识，以加工有效的对抗示例，这可以通过服务提供商直观地捍卫，而不返回这些消息。在本文中，我们提出了在更实用和严格的情况下提出了两种新的对抗攻击。对于商业云演讲API，我们提出了一个决定的黑匣子逆势攻击，这些攻击是唯一的最终决定。在偶变中，我们将决策的AE发电作为一个不连续的大规模全局优化问题，并通过自适应地将该复杂问题自适应地分解成一组子问题并协同优化每个问题来解决它。我们的春天是一种齐全的所有方法，它在一个广泛的流行语音和扬声器识别API，包括谷歌，阿里巴巴，微软，腾讯，达到100％的攻击攻击速度100％的攻击率。 iflytek，和景东，表现出最先进的黑箱攻击。对于商业语音控制设备，我们提出了Ni-Occam，第一个非交互式物理对手攻击，而对手不需要查询Oracle并且无法访问其内部信息和培训数据。我们将对抗性攻击与模型反演攻击相结合，从而产生具有高可转换性的物理有效的音频AE，而无需与目标设备的任何交互。我们的实验结果表明，NI-Occam可以成功欺骗苹果Siri，Microsoft Cortana，Google Assistant，Iflytek和Amazon Echo，平均SRO为52％和SNR为9.65dB，对抗语音控制设备的非交互式物理攻击。

Intelligent agents have great potential as facilitators of group conversation among older adults. However, little is known about how to design agents for this purpose and user group, especially in terms of agent embodiment. To this end, we conducted a mixed methods study of older adults' reactions to voice and body in a group conversation facilitation agent. Two agent forms with the same underlying artificial intelligence (AI) and voice system were compared: a humanoid robot and a voice assistant. One preliminary study (total n=24) and one experimental study comparing voice and body morphologies (n=36) were conducted with older adults and an experienced human facilitator. Findings revealed that the artificiality of the agent, regardless of its form, was beneficial for the socially uncomfortable task of conversation facilitation. Even so, talkative personality types had a poorer experience with the "bodied" robot version. Design implications and supplementary reactions, especially to agent voice, are also discussed.

在本文中，我们使用一系列建模技术来调查抽象手机是否可以从接触语音声音中出现。实际上，该研究代表了尝试从语言使用的抽象出现的基于使用的语言学理论设备的尝试。我们的任务侧重于最简单的这样的假设抽象。我们测试了两个关于语言知识在语言上的语言知识的反对原则：基于内存的学习（MBL）和纠错学习（ECL）。泛化的过程得到了抽象语言学家与之运作，我们探讨了MBL和ECL是否可以产生类似语言抽象的语言知识。每个模型都有一个由一个扬声器产生的大量预处理语音。我们评估了这些简单模型所学到的一致性或稳定性以及它们引起抽象类别的能力。两种类型的模型在这些测试方面的票价不同。我们表明ECL模型可以从输入中可靠地识别了ECL模型可以学习抽象，并且至少可以从输入中可靠地识别到传统类型中的电话库存和分组。

最近围绕语言处理模型的复杂性的最新炒作使人们对机器获得了类似人类自然语言的指挥的乐观情绪。人工智能中自然语言理解的领域声称在这一领域取得了长足的进步，但是，在这方面和其他学科中使用“理解”的概念性清晰，使我们很难辨别我们实际上有多近的距离。目前的方法和剩余挑战的全面，跨学科的概述尚待进行。除了语言知识之外，这还需要考虑我们特定于物种的能力，以对，记忆，标签和传达我们（足够相似的）体现和位置经验。此外，测量实际约束需要严格分析当前模型的技术能力，以及对理论可能性和局限性的更深入的哲学反思。在本文中，我将所有这些观点（哲学，认知语言和技术）团结在一起，以揭开达到真实（人类般的）语言理解所涉及的挑战。通过解开当前方法固有的理论假设，我希望说明我们距离实现这一目标的实际程度，如果确实是目标。

Gender/ing guides how we view ourselves, the world around us, and each other--including non-humans. Critical voices have raised the alarm about stereotyped gendering in the design of socially embodied artificial agents like voice assistants, conversational agents, and robots. Yet, little is known about how this plays out in research and to what extent. As a first step, we critically reviewed the case of Pepper, a gender-ambiguous humanoid robot. We conducted a systematic review (n=75) involving meta-synthesis and content analysis, examining how participants and researchers gendered Pepper through stated and unstated signifiers and pronoun usage. We found that ascriptions of Pepper's gender were inconsistent, limited, and at times discordant, with little evidence of conscious gendering and some indication of researcher influence on participant gendering. We offer six challenges driving the state of affairs and a practical framework coupled with a critical checklist for centering gender in research on artificial agents.

本文报告了基准数据驱动的自动共鸣手势生成的第二个基因挑战。参与的团队使用相同的语音和运动数据集来构建手势生成系统。所有这些系统生成的运动都使用标准化的可视化管道将视频渲染到视频中，并在几个大型众包用户研究中进行了评估。与比较不同的研究论文不同，结果差异仅是由于方法之间的差异，从而实现了系统之间的直接比较。今年的数据集基于18个小时的全身运动捕获，包括手指，参与二元对话的不同人。十个团队参加了两层挑战：全身和上身手势。对于每个层，我们都评估了手势运动的人类风格及其对特定语音信号的适当性。我们的评估使人类的忠诚度与手势适当性解脱，这是该领域的主要挑战。评估结果是一场革命和启示。某些合成条件被评为比人类运动捕获更明显的人类样。据我们所知，这从未在高保真的头像上展示过。另一方面，发现所有合成运动比原始运动捕获记录要小得多。其他材料可通过项目网站https://youngwoo-yoon.github.io/geneachallenge2022/获得

Curiosity for machine agents has been a focus of lively research activity. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we conduct a comprehensive, multidisciplinary survey of the field of animal and machine curiosity. As a principal contribution of this work, we use this survey as a foundation to introduce and define what we consider to be five of the most important properties of specific curiosity: 1) directedness towards inostensible referents, 2) cessation when satisfied, 3) voluntary exposure, 4) transience, and 5) coherent long-term learning. As a second main contribution of this work, we show how these properties may be implemented together in a proof-of-concept reinforcement learning agent: we demonstrate how the properties manifest in the behaviour of this agent in a simple non-episodic grid-world environment that includes curiosity-inducing locations and induced targets of curiosity. As we would hope, our example of a computational specific curiosity agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work, therefore, presents a landmark synthesis and translation of specific curiosity to the domain of machine learning and reinforcement learning and provides a novel view into how specific curiosity operates and in the future might be integrated into the behaviour of goal-seeking, decision-making computational agents in complex environments.

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

情绪分析中最突出的任务是为文本分配情绪，并了解情绪如何在语言中表现出来。自然语言处理的一个重要观察结果是，即使没有明确提及情感名称，也可以通过单独参考事件来隐式传达情绪。在心理学中，被称为评估理论的情感理论类别旨在解释事件与情感之间的联系。评估可以被形式化为变量，通过他们认为相关的事件的人们的认知评估来衡量认知评估。其中包括评估事件是否是新颖的，如果该人认为自己负责，是否与自己的目标以及许多其他人保持一致。这样的评估解释了哪些情绪是基于事件开发的，例如，新颖的情况会引起惊喜或不确定后果的人可能引起恐惧。我们在文本中分析了评估理论对情绪分析的适用性，目的是理解注释者是否可以可靠地重建评估概念，如果可以通过文本分类器预测，以及评估概念是否有助于识别情感类别。为了实现这一目标，我们通过要求人们发短信描述触发特定情绪并披露其评估的事件来编译语料库。然后，我们要求读者重建文本中的情感和评估。这种设置使我们能够衡量是否可以纯粹从文本中恢复情绪和评估，并为判断模型的绩效指标提供人体基准。我们将文本分类方法与人类注释者的比较表明，两者都可以可靠地检测出具有相似性能的情绪和评估。我们进一步表明，评估概念改善了文本中情绪的分类。

Incivility remains a major challenge for online discussion platforms, to such an extent that even conversations between well-intentioned users can often derail into uncivil behavior. Traditionally, platforms have relied on moderators to -- with or without algorithmic assistance -- take corrective actions such as removing comments or banning users. In this work we propose a complementary paradigm that directly empowers users by proactively enhancing their awareness about existing tension in the conversation they are engaging in and actively guides them as they are drafting their replies to avoid further escalation. As a proof of concept for this paradigm, we design an algorithmic tool that provides such proactive information directly to users, and conduct a user study in a popular discussion platform. Through a mixed methods approach combining surveys with a randomized controlled experiment, we uncover qualitative and quantitative insights regarding how the participants utilize and react to this information. Most participants report finding this proactive paradigm valuable, noting that it helps them to identify tension that they may have otherwise missed and prompts them to further reflect on their own replies and to revise them. These effects are corroborated by a comparison of how the participants draft their reply when our tool warns them that their conversation is at risk of derailing into uncivil behavior versus in a control condition where the tool is disabled. These preliminary findings highlight the potential of this user-centered paradigm and point to concrete directions for future implementations.

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.

Advocates of algorithmic techniques like data mining argue that these techniques eliminate human biases from the decision-making process. But an algorithm is only as good as the data it works with. Data is frequently imperfect in ways that allow these algorithms to inherit the prejudices of prior decision makers. In other cases, data may simply reflect the widespread biases that persist in society at large. In still others, data mining can discover surprisingly useful regularities that are really just preexisting patterns of exclusion and inequality. Unthinking reliance on data mining can deny historically disadvantaged and vulnerable groups full participation in society. Worse still, because the resulting discrimination is almost always an unintentional emergent property of the algorithm's use rather than a conscious choice by its programmers, it can be unusually hard to identify the source of the problem or to explain it to a court. This Essay examines these concerns through the lens of American antidiscrimination law-more particularly, through Title

Winograd架构挑战 - 一套涉及代词参考消歧的双句话，似乎需要使用致辞知识 - 是由2011年的赫克托勒维克斯提出的。到2019年，基于大型预先训练的变压器的一些AI系统基于语言模型和微调这些问题，精度优于90％。在本文中，我们审查了Winograd架构挑战的历史并评估了其重要性。

保证案件旨在为其最高主张的真理提供合理的信心，这通常涉及安全或保障。那么一个自然的问题是，案件提供了“多少”信心？我们认为，置信度不能简化为单个属性或测量。取而代之的是，我们建议它应该基于以三种不同观点的属性为基础：正面，消极和残留疑问。积极的观点考虑了该案件的证据和总体论点结合起来的程度，以表明其主张的信念是正当的。我们为理由设置了一个高标准，要求它是不可行的。对此的主要积极度量是健全性，它将论点解释为逻辑证明。对证据的信心可以概率地表达，我们使用确认措施来确保证据的“权重”跨越了一定的阈值。此外，可以通过使用概率逻辑的参数步骤从证据中汇总概率，以产生我们所谓的索赔概率估值。负面观点记录了对案件的怀疑和挑战，通常表示为叛逆者及其探索和解决。保证开发商必须防止确认偏见，并应在制定案件时大力探索潜在的叛逆者，并应记录下来及其解决方案，以避免返工并帮助审阅者。残留疑问：世界不确定，因此并非所有潜在的叛逆者都可以解决。我们探索风险，可能认为它们是可以接受或不可避免的。但是，至关重要的是，这些判断是有意识的判断，并且在保证案例中记录下来。本报告详细介绍了这些观点，并指示了我们的保证2.0的原型工具集如何协助他们的评估。

最近，对抗机器学习攻击对实用音频信号分类系统构成了严重的安全威胁，包括语音识别，说话者识别和音乐版权检测。先前的研究主要集中在确保通过在原始信号上产生类似小噪声的扰动来攻击音频信号分类器的有效性。目前尚不清楚攻击者是否能够创建音频信号扰动，除了其攻击效果外，人类还可以很好地看待。这对于音乐信号尤其重要，因为它们经过精心制作，具有可让人的音频特征。在这项工作中，我们将对音乐信号的对抗性攻击作为一种新的感知攻击框架，将人类研究纳入对抗性攻击设计中。具体而言，我们进行了一项人类研究，以量化人类对音乐信号的变化的看法。我们邀请人类参与者根据对原始和扰动的音乐信号对进行评分，并通过回归分析对人类感知过程进行反向工程，以预测给定信号的人类感知的偏差。然后将感知感知的攻击作为优化问题提出，该问题找到了最佳的扰动信号，以最大程度地减少对回归人类感知模型的感知偏差的预测。我们使用感知感知的框架来设计对YouTube版权探测器的现实对抗音乐攻击。实验表明，感知意识攻击会产生对抗性音乐的感知质量明显优于先前的工作。

基于变压器的语言模型最近在许多自然语言任务中取得了显着的结果。但是，通常通过利用大量培训数据来实现排行榜的性能，并且很少通过将明确的语言知识编码为神经模型。这使许多人质疑语言学对现代自然语言处理的相关性。在本文中，我介绍了几个案例研究，以说明理论语言学和神经语言模型仍然相互关联。首先，语言模型通过提供一个客观的工具来测量语义距离，这对语言学家很有用，语义距离很难使用传统方法。另一方面，语言理论通过提供框架和数据源来探究我们的语言模型，以了解语言理解的特定方面，从而有助于语言建模研究。本论文贡献了三项研究，探讨了语言模型中语法 - 听觉界面的不同方面。在论文的第一部分中，我将语言模型应用于单词类灵活性的问题。我将Mbert作为语义距离测量的来源，我提供了有利于将单词类灵活性分析为方向过程的证据。在论文的第二部分中，我提出了一种方法来测量语言模型中间层的惊奇方法。我的实验表明，包含形态句法异常的句子触发了语言模型早期的惊喜，而不是语义和常识异常。最后，在论文的第三部分中，我适应了一些心理语言学研究，以表明语言模型包含了论证结构结构的知识。总而言之，我的论文在自然语言处理，语言理论和心理语言学之间建立了新的联系，以为语言模型的解释提供新的观点。

语言是协调问题的强大解决方案：他们提供了稳定的，有关我们所说的单词如何对应于我们头脑中的信仰和意图的共同期望。然而，在变量和非静止社会环境中的语言使用需要语言表征来灵活：旧词在飞行中获取新的临时或合作伙伴特定含义。在本文中，我们介绍了柴（通过推理的连续分层适应），一个分层贝叶斯的协调理论和会议组织，旨在在这两个基本观察之间调和长期张力。我们认为，沟通的中央计算问题不仅仅是传输，如在经典配方中，而是在多个时间尺度上持续学习和适应。合作伙伴特定的共同点迅速出现在数型互动中的社会推论中，而社群范围内的社会公约是稳定的前锋，这些前锋已经抽象出与多个合作伙伴的互动。我们展示了新的实证数据，展示了我们的模型为多个现象提供了对先前账户挑战的计算基础：（1）与同一合作伙伴的重复互动的更有效的参考表达的融合（2）将合作伙伴特定的共同基础转移到陌生人，并（3）交际范围的影响最终会形成。