首页 > 最新文献

ACM Computing Surveys最新文献

英文 中文
Macro Ethics Principles for Responsible AI Systems: Taxonomy and Directions 负责任的人工智能系统的宏观伦理原则:分类与方向
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-13 DOI: 10.1145/3672394
Jessica Woodgate, Nirav Ajmeri

Responsible AI must be able to make or support decisions that consider human values and can be justified by human morals. Accommodating values and morals in responsible decision making is supported by adopting a perspective of macro ethics, which views ethics through a holistic lens incorporating social context. Normative ethical principles inferred from philosophy can be used to methodically reason about ethics and make ethical judgements in specific contexts. Operationalising normative ethical principles thus promotes responsible reasoning under the perspective of macro ethics. We survey AI and computer science literature and develop a taxonomy of 21 normative ethical principles which can be operationalised in AI. We describe how each principle has previously been operationalised, highlighting key themes that AI practitioners seeking to implement ethical principles should be aware of. We envision that this taxonomy will facilitate the development of methodologies to incorporate normative ethical principles in reasoning capacities of responsible AI systems.

负责任的人工智能必须能够做出或支持考虑到人类价值观并以人类道德为依据的决策。在负责任的决策中兼顾价值观和道德观,可以从宏观伦理的角度来支持,即从结合社会背景的整体视角来看待伦理。从哲学中推论出的规范性伦理原则可用于有条不紊地推理伦理问题,并在具体情境中做出 伦理判断。因此,在宏观伦理学的视角下,规范性伦理原则的可操作性促进了负责任的推理。我们对人工智能和计算机科学文献进行了调查,并制定了 21 条可在人工智能中操作的规范性伦理原则的分类法。我们描述了每项原则以前的操作方式,强调了寻求实施伦理原则的人工智能从业人员应注意的关键主题。我们设想,该分类法将促进方法论的发展,从而将规范性伦理原则纳入负责任的人工智能系统的推理能力中。
{"title":"Macro Ethics Principles for Responsible AI Systems: Taxonomy and Directions","authors":"Jessica Woodgate, Nirav Ajmeri","doi":"10.1145/3672394","DOIUrl":"https://doi.org/10.1145/3672394","url":null,"abstract":"<p>Responsible AI must be able to make or support decisions that consider human values and can be justified by human morals. Accommodating values and morals in responsible decision making is supported by adopting a perspective of macro ethics, which views ethics through a holistic lens incorporating social context. Normative ethical principles inferred from philosophy can be used to methodically reason about ethics and make ethical judgements in specific contexts. Operationalising normative ethical principles thus promotes responsible reasoning under the perspective of macro ethics. We survey AI and computer science literature and develop a taxonomy of 21 normative ethical principles which can be operationalised in AI. We describe how each principle has previously been operationalised, highlighting key themes that AI practitioners seeking to implement ethical principles should be aware of. We envision that this taxonomy will facilitate the development of methodologies to incorporate normative ethical principles in reasoning capacities of responsible AI systems.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"37 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141315607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box 为 XAI 制定以实例为中心的反事实算法基准:从白箱到黑箱
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-12 DOI: 10.1145/3672553
Catarina Moreira, Yu-Liang Chou, Chihcheng Hsieh, Chun Ouyang, João Pereira, Joaquim Jorge

This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.

本研究通过对三种不同类型的模型:决策树(完全透明、可解释、白盒模型)、随机森林(半可解释、灰盒模型)和神经网络(完全不透明、黑盒模型)进行基准评估,研究机器学习模型对反事实解释生成的影响。我们使用文献中的四种算法(DiCE、WatcherCF、原型和 GrowingSpheresCF)在 25 个不同的数据集中测试了反事实生成过程。我们的研究结果表明(1) 不同的机器学习模型对反事实解释的生成影响不大;(2) 完全基于近似损失函数的反事实算法不具有可操作性,也不会提供有意义的解释;(3) 如果不保证反事实生成的可信度,就无法获得有意义的评估结果。如果算法的内部机制不考虑可信度,那么用目前最先进的指标进行评估,就会得出有偏差和不可靠的结论;(4) 强烈建议进行反事实检查分析,以确保对反事实解释进行有力的检查,并找出可能存在的偏差。
{"title":"Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box","authors":"Catarina Moreira, Yu-Liang Chou, Chihcheng Hsieh, Chun Ouyang, João Pereira, Joaquim Jorge","doi":"10.1145/3672553","DOIUrl":"https://doi.org/10.1145/3672553","url":null,"abstract":"<p>This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"2014 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Practical tutorial on Explainable AI Techniques 可解释人工智能技术实用教程
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-12 DOI: 10.1145/3670685
Adrien Bennetot, Ivan Donadello, Ayoub El Qadi El Haouari, Mauro Dragoni, Thomas Frossard, Benedikt Wagner, Anna Sarranti, Silvia Tulli, Maria Trocan, Raja Chatila, Andreas Holzinger, Artur d'Avila Garcez, Natalia Díaz-Rodríguez

The past years have been characterized by an upsurge in opaque automatic decision support systems, such as Deep Neural Networks (DNNs). Although DNNs have great generalization and prediction abilities, it is difficult to obtain detailed explanations for their behaviour. As opaque Machine Learning models are increasingly being employed to make important predictions in critical domains, there is a danger of creating and using decisions that are not justifiable or legitimate. Therefore, there is a general agreement on the importance of endowing DNNs with explainability. EXplainable Artificial Intelligence (XAI) techniques can serve to verify and certify model outputs and enhance them with desirable notions such as trustworthiness, accountability, transparency and fairness. This guide is intended to be the go-to handbook for anyone with a computer science background aiming to obtain an intuitive insight from Machine Learning models accompanied by explanations out-of-the-box. The article aims to rectify the lack of a practical XAI guide by applying XAI techniques in particular day-to-day models, datasets and use-cases. In each chapter, the reader will find a description of the proposed method as well as one or several examples of use with Python notebooks. These can be easily modified in order to be applied to specific applications. We also explain what the prerequisites are for using each technique, what the user will learn about them, and which tasks they are aimed at.

过去几年,不透明的自动决策支持系统(如深度神经网络(DNN))急剧增加。虽然 DNNs 具有强大的泛化和预测能力,但很难获得对其行为的详细解释。由于不透明的机器学习模型越来越多地被用于在关键领域进行重要预测,因此存在着创建和使用不合理或不合法决策的危险。因此,人们普遍认同赋予 DNN 可解释性的重要性。可解释人工智能(XAI)技术可用于验证和认证模型输出,并通过可信、负责、透明和公平等理想概念来增强模型输出。本指南旨在为具有计算机科学背景、希望从机器学习模型中获得直观见解并辅以开箱即用的解释的人提供实用手册。文章旨在通过在特定的日常模型、数据集和用例中应用 XAI 技术,纠正缺乏实用 XAI 指南的问题。在每一章中,读者都会看到对所提方法的描述,以及一个或几个使用 Python 笔记本的示例。这些示例可以很容易地进行修改,以便应用于特定的应用。我们还解释了使用每种技术的前提条件、用户将学习到的知识以及它们针对的任务。
{"title":"A Practical tutorial on Explainable AI Techniques","authors":"Adrien Bennetot, Ivan Donadello, Ayoub El Qadi El Haouari, Mauro Dragoni, Thomas Frossard, Benedikt Wagner, Anna Sarranti, Silvia Tulli, Maria Trocan, Raja Chatila, Andreas Holzinger, Artur d'Avila Garcez, Natalia Díaz-Rodríguez","doi":"10.1145/3670685","DOIUrl":"https://doi.org/10.1145/3670685","url":null,"abstract":"<p>The past years have been characterized by an upsurge in opaque automatic decision support systems, such as Deep Neural Networks (DNNs). Although DNNs have great generalization and prediction abilities, it is difficult to obtain detailed explanations for their behaviour. As opaque Machine Learning models are increasingly being employed to make important predictions in critical domains, there is a danger of creating and using decisions that are not justifiable or legitimate. Therefore, there is a general agreement on the importance of endowing DNNs with explainability. EXplainable Artificial Intelligence (XAI) techniques can serve to verify and certify model outputs and enhance them with desirable notions such as trustworthiness, accountability, transparency and fairness. This guide is intended to be the go-to handbook for anyone with a computer science background aiming to obtain an intuitive insight from Machine Learning models accompanied by explanations out-of-the-box. The article aims to rectify the lack of a practical XAI guide by applying XAI techniques in particular day-to-day models, datasets and use-cases. In each chapter, the reader will find a description of the proposed method as well as one or several examples of use with Python notebooks. These can be easily modified in order to be applied to specific applications. We also explain what the prerequisites are for using each technique, what the user will learn about them, and which tasks they are aimed at.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"6 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Survey of Hardware Improvements to Secure Program Execution 安全程序执行硬件改进调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-12 DOI: 10.1145/3672392
Lianying Zhao, He Shuang, Shengjie Xu, Wei Huang, Rongzhen Cui, Pushkar Bettadpur, David Lie

Hardware has been constantly augmented for security considerations since the advent of computers. There is also a common perception among computer users that hardware does a relatively better job on security assurance compared to software. Yet, the community has long lacked a comprehensive study to answer questions such as how hardware security support contributes to security, what kind of improvements have been introduced to improve such support and what its advantages/disadvantages are.

By generalizing various security goals, we taxonomize hardware security features and their security properties that can aid in securing program execution, considered as three aspects, i.e., state correctness, runtime protection and input/output protection. Based on this taxonomy, the survey systematically examines 1) the roles: how hardware is applied to achieve security; and 2) the problems: how reported attacks have exploited certain defects in hardware. We see that hardware’s unique advantages and problems co-exist and it highly depends on the desired security purpose as to which type to use. Among the survey findings are also that code as part of hardware (aka. firmware) should be treated differently to ensure security by design; and how research proposals have driven the advancement of commodity hardware features.

自计算机问世以来,出于安全考虑,硬件一直在不断增强。计算机用户也普遍认为,与软件相比,硬件在安全保障方面做得更好。然而,长期以来,业界一直缺乏一项全面的研究来回答硬件安全支持对安全的贡献、为改善硬件安全支持所做的改进以及硬件安全支持的优缺点等问题。通过归纳各种安全目标,我们对硬件安全特性及其有助于确保程序执行安全的安全属性进行了分类,分为三个方面,即状态正确性、运行时保护和输入/输出保护。在此分类法的基础上,调查系统地研究了 1) 作用:如何应用硬件来实现安全;以及 2) 问题:所报告的攻击是如何利用硬件中的某些缺陷的。我们发现,硬件的独特优势与问题并存,使用哪种类型的硬件在很大程度上取决于所需的安全目的。调查结果还包括:应区别对待作为硬件一部分的代码(又称固件),以确保设计的安全性;以及研究提案如何推动了商品硬件功能的进步。
{"title":"A Survey of Hardware Improvements to Secure Program Execution","authors":"Lianying Zhao, He Shuang, Shengjie Xu, Wei Huang, Rongzhen Cui, Pushkar Bettadpur, David Lie","doi":"10.1145/3672392","DOIUrl":"https://doi.org/10.1145/3672392","url":null,"abstract":"<p>Hardware has been constantly augmented for security considerations since the advent of computers. There is also a common perception among computer users that hardware does a relatively better job on security assurance compared to software. Yet, the community has long lacked a comprehensive study to answer questions such as how hardware security support contributes to security, what kind of improvements have been introduced to improve such support and what its advantages/disadvantages are. </p><p>By generalizing various security goals, we taxonomize hardware security features and their security properties that can aid in securing program execution, considered as three aspects, i.e., state correctness, runtime protection and input/output protection. Based on this taxonomy, the survey systematically examines 1) the roles: how hardware is applied to achieve security; and 2) the problems: how reported attacks have exploited certain defects in hardware. We see that hardware’s unique advantages and problems co-exist and it highly depends on the desired security purpose as to which type to use. Among the survey findings are also that code as part of hardware (aka. firmware) should be treated differently to ensure security by design; and how research proposals have driven the advancement of commodity hardware features.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"36 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Lexical Semantic Change through Large Language Models: a Survey 通过大型语言模型实现词汇语义变化:一项调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-10 DOI: 10.1145/3672393
Francesco Periti, Stefano Montanelli

Lexical Semantic Change (LSC) is the task of identifying, interpreting, and assessing the possible change over time in the meanings of a target word. Traditionally, LSC has been addressed by linguists and social scientists through manual and time-consuming analyses, which have thus been limited in terms of the volume, genres, and time-frame that can be considered. In recent years, computational approaches based on Natural Language Processing have gained increasing attention to automate LSC as much as possible. Significant advancements have been made by relying on Large Language Models (LLMs), which can handle the multiple usages of the words and better capture the related semantic change. In this article, we survey the approaches based on LLMs for LSC and we propose a classification framework characterized by three dimensions: meaning representation, time-awareness, and learning modality. The framework is exploited to i) review the measures for change assessment, ii) compare the approaches on performance, and iii) discuss the current issues in terms of scalability, interpretability, and robustness. Open challenges and future research directions about the use of LLMs for LSC are finally outlined.

词义变化(LSC)是指识别、解释和评估目标词的词义随时间推移可能发生的变化。传统上,语言学家和社会科学家都是通过耗时的人工分析来处理 LSC 问题的,因此在可考虑的数量、流派和时间范围方面都受到了限制。近年来,基于自然语言处理的计算方法受到越来越多的关注,以尽可能实现 LSC 自动化。大型语言模型(LLM)可以处理词语的多种用法,并能更好地捕捉相关语义变化,因此在这方面取得了重大进展。在本文中,我们对基于 LLM 的 LSC 方法进行了调查,并提出了一个分类框架,其特点包括三个方面:意义表示、时间感知和学习模式。利用该框架,我们可以:i) 回顾变化评估的措施;ii) 比较各种方法的性能;iii) 讨论当前在可扩展性、可解释性和鲁棒性方面存在的问题。最后概述了将 LLMs 用于 LSC 所面临的挑战和未来的研究方向。
{"title":"Lexical Semantic Change through Large Language Models: a Survey","authors":"Francesco Periti, Stefano Montanelli","doi":"10.1145/3672393","DOIUrl":"https://doi.org/10.1145/3672393","url":null,"abstract":"<p>Lexical Semantic Change (LSC) is the task of identifying, interpreting, and assessing the possible change over time in the meanings of a target word. Traditionally, LSC has been addressed by linguists and social scientists through manual and time-consuming analyses, which have thus been limited in terms of the volume, genres, and time-frame that can be considered. In recent years, computational approaches based on Natural Language Processing have gained increasing attention to automate LSC as much as possible. Significant advancements have been made by relying on Large Language Models (LLMs), which can handle the multiple usages of the words and better capture the related semantic change. In this article, we survey the approaches based on LLMs for LSC and we propose a classification framework characterized by three dimensions: <i>meaning representation</i>, <i>time-awareness</i>, and <i>learning modality</i>. The framework is exploited to i) review the measures for change assessment, ii) compare the approaches on performance, and iii) discuss the current issues in terms of scalability, interpretability, and robustness. Open challenges and future research directions about the use of LLMs for LSC are finally outlined.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"31 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141299114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Databases in Edge and Fog Environments : A Survey 边缘和雾环境中的数据库 :调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-04 DOI: 10.1145/3666001
Luís Manuel Meruje Ferreira, Fabio Coelho, José Pereira

While a significant number of databases are deployed in cloud environments, pushing part or all data storage and querying planes closer to their sources (i.e., to the edge) can provide advantages in latency, connectivity, privacy, energy and scalability. This article dissects the advantages provided by databases in edge and fog environments, by surveying application domains and discussing the key drivers for pushing database systems to the edge. At the same time, it also identifies the main challenges faced by developers in this new environment, and analysis the mechanisms employed to deal with them. By providing an overview of the current state of edge and fog databases, this survey provides valuable insights into future research directions.

虽然大量数据库部署在云环境中,但将部分或全部数据存储和查询平面推向更靠近数据源的地方(即边缘),可以在延迟、连接性、隐私、能源和可扩展性方面提供优势。本文通过调查应用领域和讨论将数据库系统推向边缘的关键驱动因素,剖析了数据库在边缘和雾环境中提供的优势。同时,文章还指出了开发人员在这种新环境中面临的主要挑战,并分析了应对这些挑战的机制。通过概述边缘和雾数据库的现状,本调查报告为未来的研究方向提供了宝贵的见解。
{"title":"Databases in Edge and Fog Environments : A Survey","authors":"Luís Manuel Meruje Ferreira, Fabio Coelho, José Pereira","doi":"10.1145/3666001","DOIUrl":"https://doi.org/10.1145/3666001","url":null,"abstract":"<p>While a significant number of databases are deployed in cloud environments, pushing part or all data storage and querying planes closer to their sources (i.e., to the edge) can provide advantages in latency, connectivity, privacy, energy and scalability. This article dissects the advantages provided by databases in edge and fog environments, by surveying application domains and discussing the key drivers for pushing database systems to the edge. At the same time, it also identifies the main challenges faced by developers in this new environment, and analysis the mechanisms employed to deal with them. By providing an overview of the current state of edge and fog databases, this survey provides valuable insights into future research directions.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"69 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Machine Learning with Confidential Computing: A Systematization of Knowledge 利用保密计算进行机器学习:知识系统化
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-03 DOI: 10.1145/3670007
Fan Mo, Zahra Tarkhani, Hamed Haddadi

Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML’s pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this paper, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide iconfidentiality guarantees and iiintegrity assurances, and discuss their advanced features and drawbacks. Key challenges are further identified, and we provide dedicated analyses of the limitations in existing Trusted Execution Environment (TEE) systems for ML use cases. Finally, prospective works are discussed, including grounded privacy definitions for closed-loop protection, partitioned executions of efficient ML, dedicated TEE-assisted designs for ML, TEE-aware ML, and ML full pipeline guarantees. By providing these potential solutions in our systematization of knowledge, we aim to build the bridge to help achieve a much stronger TEE-enabled ML for privacy guarantees without introducing computation and system costs.

随着机器学习(ML)的普遍发展和最近展示的巨大攻击面,机器学习(ML)中的隐私和安全挑战变得日益严峻。作为一种成熟的面向系统的方法,保密计算已被学术界和工业界用于缓解各种 ML 场景中的隐私和安全问题。本文研究了 ML 与保密计算之间的结合。我们系统梳理了保密计算辅助 ML 技术(提供 i) 保密性保证和 ii) 完整性保证)的前期工作,并讨论了它们的先进功能和缺点。我们进一步确定了关键挑战,并专门分析了用于 ML 用例的现有可信执行环境 (TEE) 系统的局限性。最后,我们讨论了前瞻性工作,包括闭环保护的基础隐私定义、高效 ML 的分区执行、ML 的专用 TEE 辅助设计、TEE 感知 ML 和 ML 全流水线保证。通过在我们的知识系统化中提供这些潜在的解决方案,我们旨在搭建一座桥梁,帮助实现更强大的 TEE 支持的 ML,从而在不引入计算和系统成本的情况下实现隐私保证。
{"title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","authors":"Fan Mo, Zahra Tarkhani, Hamed Haddadi","doi":"10.1145/3670007","DOIUrl":"https://doi.org/10.1145/3670007","url":null,"abstract":"<p>Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML’s pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential Computing has been utilized in both academia and industry to mitigate privacy and security issues in various ML scenarios. In this paper, the conjunction between ML and Confidential Computing is investigated. We systematize the prior work on Confidential Computing-assisted ML techniques that provide <i>i</i>) <i>confidentiality guarantees</i> and <i>ii</i>) <i>integrity assurances</i>, and discuss their advanced features and drawbacks. Key challenges are further identified, and we provide dedicated analyses of the <i>limitations</i> in existing <i>Trusted Execution Environment</i> (TEE) systems for ML use cases. Finally, prospective works are discussed, including grounded privacy definitions for closed-loop protection, partitioned executions of efficient ML, dedicated TEE-assisted designs for ML, TEE-aware ML, and ML full pipeline guarantees. By providing these potential solutions in our systematization of knowledge, we aim to build the bridge to help achieve a much stronger TEE-enabled ML for privacy guarantees without introducing computation and system costs.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"2013 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
“Are you feeling sick?” A systematic literature review of cybersickness in virtual reality "你感觉不舒服吗?虚拟现实中的网络病症系统文献综述
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-03 DOI: 10.1145/3670008
Nilotpal Biswas, Anamitra Mukherjee, Samit Bhattacharya

Cybersickness (CS), also known as visually induced motion sickness (VIMS) is a condition that can affect individuals when they interact with virtual reality (VR) technology. This condition is characterized by symptoms such as nausea, dizziness, headaches, eye fatigue, etc., and can be caused by a variety of factors. Finding a feasible solution to reduce the impact of CS is extremely important as it will greatly enhance the overall user experience and make VR more appealing to a wider range of people. We have carefully compiled a list of 223 highly pertinent studies to review the current state of research on the most essential aspects of CS. We have provided a novel taxonomy that encapsulates various aspects of CS measurement techniques found in the literature. We have proposed a set of CS mitigation guidelines for both developers and users. We have also discussed various CS-inducing factors and provided a taxonomy that tries to capture the same. Overall, our work provides a comprehensive overview of the current state of research in CS with a particular emphasis on different measurement techniques and CS mitigation strategies, identifies research gaps in the literature, and provides recommendations for future research in the field.

晕动症(CS),又称视觉诱发晕动病(VIMS),是一种在与虚拟现实(VR)技术交互时可能影响个人的病症。这种症状的特点是恶心、头晕、头痛、眼睛疲劳等,可由多种因素引起。找到一种可行的解决方案来减少 CS 的影响极为重要,因为这将大大提升用户的整体体验,使 VR 对更多人更具吸引力。我们精心编制了一份包含 223 项高度相关研究的清单,以回顾有关 CS 最基本方面的研究现状。我们提供了一个新颖的分类法,囊括了文献中发现的 CS 测量技术的各个方面。我们为开发人员和用户提出了一套 CS 缓解指南。我们还讨论了各种诱发 CS 的因素,并提供了一个试图捕捉这些因素的分类法。总之,我们的工作全面概述了 CS 的研究现状,特别强调了不同的测量技术和 CS 缓解策略,确定了文献中的研究空白,并为该领域的未来研究提供了建议。
{"title":"“Are you feeling sick?” A systematic literature review of cybersickness in virtual reality","authors":"Nilotpal Biswas, Anamitra Mukherjee, Samit Bhattacharya","doi":"10.1145/3670008","DOIUrl":"https://doi.org/10.1145/3670008","url":null,"abstract":"<p>Cybersickness (CS), also known as visually induced motion sickness (VIMS) is a condition that can affect individuals when they interact with virtual reality (VR) technology. This condition is characterized by symptoms such as nausea, dizziness, headaches, eye fatigue, etc., and can be caused by a variety of factors. Finding a feasible solution to reduce the impact of CS is extremely important as it will greatly enhance the overall user experience and make VR more appealing to a wider range of people. We have carefully compiled a list of 223 highly pertinent studies to review the current state of research on the most essential aspects of CS. We have provided a novel taxonomy that encapsulates various aspects of CS measurement techniques found in the literature. We have proposed a set of CS mitigation guidelines for both developers and users. We have also discussed various CS-inducing factors and provided a taxonomy that tries to capture the same. Overall, our work provides a comprehensive overview of the current state of research in CS with a particular emphasis on different measurement techniques and CS mitigation strategies, identifies research gaps in the literature, and provides recommendations for future research in the field.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"70 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advancements in Federated Learning: Models, Methods, and Privacy 联合学习的进步:模式、方法和隐私
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-06-01 DOI: 10.1145/3664650
Huiming Chen, Huandong Wang, Qingyue Long, Depeng Jin, Yong Li

Federated learning (FL) is a promising technique for resolving the rising privacy and security concerns. Its main ingredient is to cooperatively learn the model among the distributed clients without uploading any sensitive data. In this paper, we conducted a thorough review of the related works, following the development context and deeply mining the key technologies behind FL from the perspectives of theory and application. Specifically, we first classify the existing works in FL architecture based on the network topology of FL systems with detailed analysis and summarization. Next, we abstract the current application problems, summarize the general techniques and frame the application problems into the general paradigm of FL base models. Moreover, we provide our proposed solutions for model training via FL. We have summarized and analyzed the existing FedOpt algorithms, and deeply revealed the algorithmic development principles of many first-order algorithms in depth, proposing a more generalized algorithm design framework. With the instantiation of these frameworks, FedOpt algorithms can be simply developed. As privacy and security is the fundamental requirement in FL, we provide the existing attack scenarios and the defense methods. To the best of our knowledge, we are among the first tier to review the theoretical methodology and propose our strategies since there are very few works surveying the theoretical approaches. Our survey targets motivating the development of high-performance, privacy-preserving, and secure methods to integrate FL into real-world applications.

联合学习(FL)是解决日益增长的隐私和安全问题的一种有前途的技术。其主要内容是在不上传任何敏感数据的情况下,在分布式客户端之间合作学习模型。在本文中,我们对相关工作进行了全面回顾,遵循发展脉络,从理论和应用的角度深入挖掘了 FL 背后的关键技术。具体来说,我们首先根据 FL 系统的网络拓扑结构对 FL 架构的现有工作进行了分类,并进行了详细的分析和总结。接着,我们抽象出当前的应用问题,总结出通用技术,并将应用问题框定到 FL 基础模型的一般范式中。此外,我们还提出了通过 FL 进行模型训练的解决方案。我们总结分析了现有的 FedOpt 算法,深入揭示了许多一阶算法的算法开发原理,提出了更具普适性的算法设计框架。通过这些框架的实例化,可以简单地开发出 FedOpt 算法。由于隐私和安全是 FL 的基本要求,我们提供了现有的攻击场景和防御方法。据我们所知,我们是第一批回顾理论方法并提出我们的策略的人,因为很少有著作调查理论方法。我们的调查旨在激励开发高性能、保护隐私和安全的方法,以便将 FL 集成到现实世界的应用中。
{"title":"Advancements in Federated Learning: Models, Methods, and Privacy","authors":"Huiming Chen, Huandong Wang, Qingyue Long, Depeng Jin, Yong Li","doi":"10.1145/3664650","DOIUrl":"https://doi.org/10.1145/3664650","url":null,"abstract":"<p>Federated learning (FL) is a promising technique for resolving the rising privacy and security concerns. Its main ingredient is to cooperatively learn the model among the distributed clients without uploading any sensitive data. In this paper, we conducted a thorough review of the related works, following the development context and deeply mining the key technologies behind FL from the perspectives of theory and application. Specifically, we first classify the existing works in FL architecture based on the network topology of FL systems with detailed analysis and summarization. Next, we abstract the current application problems, summarize the general techniques and frame the application problems into the general paradigm of FL base models. Moreover, we provide our proposed solutions for model training via FL. We have summarized and analyzed the existing FedOpt algorithms, and deeply revealed the algorithmic development principles of many first-order algorithms in depth, proposing a more generalized algorithm design framework. With the instantiation of these frameworks, FedOpt algorithms can be simply developed. As privacy and security is the fundamental requirement in FL, we provide the existing attack scenarios and the defense methods. To the best of our knowledge, we are among the first tier to review the theoretical methodology and propose our strategies since there are very few works surveying the theoretical approaches. Our survey targets motivating the development of high-performance, privacy-preserving, and secure methods to integrate FL into real-world applications.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"21 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research Progress of EEG-Based Emotion Recognition: A Survey 基于脑电图的情绪识别研究进展:调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-28 DOI: 10.1145/3666002
Yiming Wang, Bin Zhang, Lamei Di

Emotion recognition based on electroencephalography (EEG) signals has emerged as a prominent research field, facilitating objective evaluation of diseases like depression and motion detection for heathy people. Starting from the basic concepts of temporal-frequency-spatial features in EEG and the methods for cross-domain feature fusion. This survey then extends the overfitting challenge of EEG single-modal to the problem of heterogeneous modality modeling in multi-modal conditions. It explores issues such as feature selection, sample scarcity, cross-subject emotional transfer, physiological knowledge discovery, multi-modal fusion methods and modality missing. These findings provide clues for researchers to further investigate emotion recognition based on EEG signals.

基于脑电图(EEG)信号的情绪识别已成为一个突出的研究领域,有助于对抑郁症等疾病进行客观评估和对健康人进行运动检测。本研究从脑电信号的时间-频率-空间特征的基本概念和跨域特征融合方法入手。然后,本研究将脑电图单模态过拟合挑战扩展到多模态条件下的异构模态建模问题。它探讨了特征选择、样本稀缺性、跨主体情感转移、生理知识发现、多模态融合方法和模态缺失等问题。这些发现为研究人员进一步研究基于脑电信号的情感识别提供了线索。
{"title":"Research Progress of EEG-Based Emotion Recognition: A Survey","authors":"Yiming Wang, Bin Zhang, Lamei Di","doi":"10.1145/3666002","DOIUrl":"https://doi.org/10.1145/3666002","url":null,"abstract":"<p>Emotion recognition based on electroencephalography (EEG) signals has emerged as a prominent research field, facilitating objective evaluation of diseases like depression and motion detection for heathy people. Starting from the basic concepts of temporal-frequency-spatial features in EEG and the methods for cross-domain feature fusion. This survey then extends the overfitting challenge of EEG single-modal to the problem of heterogeneous modality modeling in multi-modal conditions. It explores issues such as feature selection, sample scarcity, cross-subject emotional transfer, physiological knowledge discovery, multi-modal fusion methods and modality missing. These findings provide clues for researchers to further investigate emotion recognition based on EEG signals.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"26 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
ACM Computing Surveys
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1