首页 > 最新文献

ACM Computing Surveys最新文献

英文 中文
A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities 人工智能的鲁棒性:从以人为本的角度看技术挑战与机遇
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-27 DOI: 10.1145/3665926
Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, Jie Yang

Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Besides, robustness is interpreted differently across domains and contexts of AI. In this work, we systematically survey recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: 1) methods and approaches that address robustness in different phases of the machine learning pipeline; 2) methods improving robustness in specific model architectures, tasks, and systems; and in addition, 3) methodologies and insights around evaluating the robustness of AI systems, particularly the trade-offs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge they can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

尽管人工智能(AI)系统的性能令人印象深刻,但其鲁棒性仍然难以捉摸,成为阻碍大规模应用的关键问题。此外,在不同的人工智能领域和环境中,对鲁棒性的解释也不尽相同。在这项工作中,我们系统地调查了最近的进展,为人工智能的鲁棒性提供了一个协调的概念术语。我们引入了三个分类法,从基础和应用的角度来组织和描述文献:1)在机器学习管道的不同阶段解决鲁棒性问题的方法和途径;2)在特定模型架构、任务和系统中提高鲁棒性的方法;此外,3)评估人工智能系统鲁棒性的方法和见解,特别是与其他可信性属性之间的权衡。最后,我们确定并讨论了研究差距和机遇,并对该领域进行了展望。我们强调了人类在评估和增强人工智能鲁棒性方面的核心作用,考虑了人类可以提供的必要知识,并讨论了未来更好地理解实践和开发辅助工具的必要性。
{"title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","authors":"Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, Jie Yang","doi":"10.1145/3665926","DOIUrl":"https://doi.org/10.1145/3665926","url":null,"abstract":"<p>Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Besides, robustness is interpreted differently across domains and contexts of AI. In this work, we systematically survey recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: 1) methods and approaches that address robustness in different phases of the machine learning pipeline; 2) methods improving robustness in specific model architectures, tasks, and systems; and in addition, 3) methodologies and insights around evaluating the robustness of AI systems, particularly the trade-offs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge they can provide, and discuss the need for better understanding practices and developing supportive tools in the future.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"65 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251746","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
Human Image Generation: A Comprehensive Survey 人类图像生成:全面调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-22 DOI: 10.1145/3665869
Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan

Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value. Many researchers have been devoted to synthesizing high-fidelity human images as one of the most commonly seen object categories in daily lives, where a large number of studies are performed based on various models, task settings and applications. Thus, it is necessary to give a comprehensive overview on these variant methods on human image generation. In this paper, we divide human image generation techniques into three paradigms, i.e., data-driven methods, knowledge-guided methods and hybrid methods. For each paradigm, the most representative models and the corresponding variants are presented, where the advantages and characteristics of different methods are summarized in terms of model architectures. Besides, the main public human image datasets and evaluation metrics in the literature are summarized. Furthermore, due to the wide application potentials, the typical downstream usages of synthesized human images are covered. Finally, the challenges and potential opportunities of human image generation are discussed to shed light on future research.

随着深度生成模型的发展,图像和视频合成因其巨大的学术和应用价值,已成为计算机视觉和机器学习领域一个蓬勃发展的课题。作为日常生活中最常见的对象类别之一,许多研究人员都致力于合成高保真人体图像,并基于各种模型、任务设置和应用进行了大量研究。因此,有必要对这些不同的人体图像生成方法进行全面概述。本文将人类图像生成技术分为三种范式,即数据驱动法、知识引导法和混合法。针对每种范式,我们都介绍了最具代表性的模型和相应的变体,并从模型架构的角度总结了不同方法的优势和特点。此外,还总结了文献中主要的公共人类图像数据集和评估指标。此外,由于合成人体图像具有广泛的应用潜力,还介绍了合成人体图像的典型下游用途。最后,讨论了人类图像生成所面临的挑战和潜在机遇,为未来研究提供启示。
{"title":"Human Image Generation: A Comprehensive Survey","authors":"Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan","doi":"10.1145/3665869","DOIUrl":"https://doi.org/10.1145/3665869","url":null,"abstract":"<p>Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value. Many researchers have been devoted to synthesizing high-fidelity human images as one of the most commonly seen object categories in daily lives, where a large number of studies are performed based on various models, task settings and applications. Thus, it is necessary to give a comprehensive overview on these variant methods on human image generation. In this paper, we divide human image generation techniques into three paradigms, i.e., data-driven methods, knowledge-guided methods and hybrid methods. For each paradigm, the most representative models and the corresponding variants are presented, where the advantages and characteristics of different methods are summarized in terms of model architectures. Besides, the main public human image datasets and evaluation metrics in the literature are summarized. Furthermore, due to the wide application potentials, the typical downstream usages of synthesized human images are covered. Finally, the challenges and potential opportunities of human image generation are discussed to shed light on future research.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"124 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251571","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 on Malware Detection with Graph Representation Learning 利用图表示学习进行恶意软件检测的调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-21 DOI: 10.1145/3664649
Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha, Anis Zouaoui

Malware detection has become a major concern due to the increasing number and complexity of malware. Traditional detection methods based on signatures and heuristics are used for malware detection, but unfortunately, they suffer from poor generalization to unknown attacks and can be easily circumvented using obfuscation techniques. In recent years, Machine Learning (ML) and notably Deep Learning (DL) achieved impressive results in malware detection by learning useful representations from data and have become a solution preferred over traditional methods. Recently, the application of Graph Representation Learning (GRL) techniques on graph-structured data has demonstrated impressive capabilities in malware detection. This success benefits notably from the robust structure of graphs, which are challenging for attackers to alter, and their intrinsic explainability capabilities. In this survey, we provide an in-depth literature review to summarize and unify existing works under the common approaches and architectures. We notably demonstrate that Graph Neural Networks (GNNs) reach competitive results in learning robust embeddings from malware represented as expressive graph structures such as Function Call Graphs (FCGs) and Control Flow Graphs (CFGs). This study also discusses the robustness of GRL-based methods to adversarial attacks, contrasts their effectiveness with other ML/DL approaches, and outlines future research for practical deployment.

由于恶意软件的数量和复杂性不断增加,恶意软件检测已成为一个主要问题。传统的恶意软件检测方法基于签名和启发式方法,但遗憾的是,这些方法对未知攻击的泛化能力较差,而且很容易被混淆技术所规避。近年来,机器学习(ML),尤其是深度学习(DL)通过从数据中学习有用的表征,在恶意软件检测方面取得了令人瞩目的成果,并已成为一种优于传统方法的解决方案。最近,图表示学习(GRL)技术在图结构数据上的应用已在恶意软件检测中展现出令人印象深刻的能力。这种成功主要得益于图的强大结构(攻击者很难改变这种结构)及其内在的可解释性。在本调查报告中,我们对文献进行了深入回顾,总结并统一了通用方法和架构下的现有工作。值得注意的是,我们证明了图神经网络(GNN)在从以函数调用图(FCG)和控制流图(CFG)等表现性图结构表示的恶意软件中学习稳健嵌入方面取得了有竞争力的结果。本研究还讨论了基于 GRL 的方法对对抗性攻击的鲁棒性,对比了它们与其他 ML/DL 方法的有效性,并概述了未来的实际部署研究。
{"title":"A Survey on Malware Detection with Graph Representation Learning","authors":"Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha, Anis Zouaoui","doi":"10.1145/3664649","DOIUrl":"https://doi.org/10.1145/3664649","url":null,"abstract":"<p>Malware detection has become a major concern due to the increasing number and complexity of malware. Traditional detection methods based on signatures and heuristics are used for malware detection, but unfortunately, they suffer from poor generalization to unknown attacks and can be easily circumvented using obfuscation techniques. In recent years, Machine Learning (ML) and notably Deep Learning (DL) achieved impressive results in malware detection by learning useful representations from data and have become a solution preferred over traditional methods. Recently, the application of Graph Representation Learning (GRL) techniques on graph-structured data has demonstrated impressive capabilities in malware detection. This success benefits notably from the robust structure of graphs, which are challenging for attackers to alter, and their intrinsic explainability capabilities. In this survey, we provide an in-depth literature review to summarize and unify existing works under the common approaches and architectures. We notably demonstrate that Graph Neural Networks (GNNs) reach competitive results in learning robust embeddings from malware represented as expressive graph structures such as Function Call Graphs (FCGs) and Control Flow Graphs (CFGs). This study also discusses the robustness of GRL-based methods to adversarial attacks, contrasts their effectiveness with other ML/DL approaches, and outlines future research for practical deployment.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"12 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251731","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
Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit 代码智能深度学习:调查、基准和工具包
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-18 DOI: 10.1145/3664597
Yao Wan, Zhangqian Bi, Yang He, Jianguo Zhang, Hongyu Zhang, Yulei Sui, Guandong Xu, Hai Jin, Philip Yu

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineering, machine learning, data mining, natural language processing, and programming languages. In this paper, we conduct a comprehensive literature review on deep learning for code intelligence, from the aspects of code representation learning, deep learning techniques, and application tasks. We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models. In particular, we inspect the existing code intelligence models under the basis of code representation learning, and provide a comprehensive overview to enhance comprehension of the present state of code intelligence. Furthermore, we publicly release the source code and data resources to provide the community with a ready-to-use benchmark, which can facilitate the evaluation and comparison of existing and future code intelligence models (https://xcodemind.github.io). At last, we also point out several challenging and promising directions for future research.

代码智能利用机器学习技术从大量代码库中提取知识,目的是开发智能工具,提高计算机编程的质量和生产率。目前,专注于代码智能的研究社区已经蓬勃发展,研究领域涉及软件工程、机器学习、数据挖掘、自然语言处理和编程语言。在本文中,我们从代码表示学习、深度学习技术和应用任务等方面,对用于代码智能的深度学习进行了全面的文献综述。我们还对几种最先进的代码智能神经模型进行了基准测试,并为基于深度学习的代码智能模型的快速原型开发提供了一个开源工具包。特别是,我们在代码表示学习的基础上考察了现有的代码智能模型,并提供了一个全面的概述,以加深对代码智能现状的理解。此外,我们还公开发布了源代码和数据资源,为社会各界提供了一个现成可用的基准,便于对现有和未来的代码智能模型(https://xcodemind.github.io)进行评估和比较。最后,我们还指出了几个具有挑战性和前景的未来研究方向。
{"title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","authors":"Yao Wan, Zhangqian Bi, Yang He, Jianguo Zhang, Hongyu Zhang, Yulei Sui, Guandong Xu, Hai Jin, Philip Yu","doi":"10.1145/3664597","DOIUrl":"https://doi.org/10.1145/3664597","url":null,"abstract":"<p>Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineering, machine learning, data mining, natural language processing, and programming languages. In this paper, we conduct a comprehensive literature review on deep learning for code intelligence, from the aspects of code representation learning, deep learning techniques, and application tasks. We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models. In particular, we inspect the existing code intelligence models under the basis of code representation learning, and provide a comprehensive overview to enhance comprehension of the present state of code intelligence. Furthermore, we publicly release the source code and data resources to provide the community with a ready-to-use benchmark, which can facilitate the evaluation and comparison of existing and future code intelligence models (https://xcodemind.github.io). At last, we also point out several challenging and promising directions for future research.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"191 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251603","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 Unified Review of Deep Learning for Automated Medical Coding 深度学习在医疗自动编码中的应用综述
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-17 DOI: 10.1145/3664615
Shaoxiong Ji, Xiaobo Li, Wei Sun, Hang Dong, Ara Taalas, Yijia Zhang, Honghan Wu, Esa Pitkänen, Pekka Marttinen

Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.

自动医疗编码是医疗运营和交付的一项重要任务,它通过预测临床文件中的医疗编码来管理非结构化数据。深度学习和自然语言处理领域的最新进展已被广泛应用于这项任务。然而,基于深度学习的医疗编码缺乏统一的神经网络架构设计观点。本综述提出了一个统一的框架,以提供对医疗编码模型构件的一般理解,并总结了拟议框架下的近期先进模型。我们的统一框架将医学编码分解为四个主要部分,即用于文本特征提取的编码器模块、构建深度编码器架构的机制、将隐藏表征转化为医学代码的解码器模块以及辅助信息的使用。最后,我们介绍了基准和实际使用情况,并讨论了主要研究挑战和未来方向。
{"title":"A Unified Review of Deep Learning for Automated Medical Coding","authors":"Shaoxiong Ji, Xiaobo Li, Wei Sun, Hang Dong, Ara Taalas, Yijia Zhang, Honghan Wu, Esa Pitkänen, Pekka Marttinen","doi":"10.1145/3664615","DOIUrl":"https://doi.org/10.1145/3664615","url":null,"abstract":"<p>Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"8 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251600","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
Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search 神经网络设计的高效自动化:可微分神经架构搜索调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-15 DOI: 10.1145/3665138
Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia

In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.

在过去几年中,可微分神经架构搜索(DNAS)迅速成为自动发现深度神经网络架构的潮流方法。这种崛起主要归功于 DARTS(可微分神经架构搜索)的流行,它是最早的主要 DNAS 方法之一。与之前基于强化学习或进化算法的工作相比,DNAS 的速度快了几个数量级,而且使用的计算资源更少。在这份综合调查报告中,我们特别关注 DNAS,并回顾了该领域的最新方法。此外,我们还提出了一种新颖的基于挑战的分类法,用于对 DNAS 方法进行分类。我们还讨论了 DNAS 在过去几年中的贡献及其对全球 NAS 领域的影响。最后,我们对 DNAS 领域未来的研究方向提出了一些见解。
{"title":"Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search","authors":"Alexandre Heuillet, Ahmad Nasser, Hichem Arioui, Hedi Tabia","doi":"10.1145/3665138","DOIUrl":"https://doi.org/10.1145/3665138","url":null,"abstract":"<p>In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"8 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141251577","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
An Overview of Privacy-Enhancing Technologies in Biometric Recognition 生物识别中的隐私增强技术概览
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-14 DOI: 10.1145/3664596
Pietro Melzi, Christian Rathgeb, Ruben Tolosana, Ruben Vera, Christoph Busch

Privacy-enhancing technologies are technologies that implement fundamental data protection principles. With respect to biometric recognition, different types of privacy-enhancing technologies have been introduced for protecting stored biometric data which are generally classified as sensitive. In this regard, various taxonomies and conceptual categorizations have been proposed and standardisation activities have been carried out. However, these efforts have mainly been devoted to certain sub-categories of privacy-enhancing technologies and therefore lack generalization. This work provides an overview of concepts of privacy-enhancing technologies for biometric recognition in a unified framework. Key properties and differences between existing concepts are highlighted in detail at each processing step. Fundamental characteristics and limitations of existing technologies are discussed and related to data protection techniques and principles. Moreover, scenarios and methods for the assessment of privacy-enhancing technologies for biometric recognition are presented. This paper is meant as a point of entry to the field of data protection for biometric recognition applications and is directed towards experienced researchers as well as non-experts.

隐私增强技术是实施基本数据保护原则的技术。在生物识别方面,已经引入了不同类型的隐私增强技术来保护存储的生物识别数据,这些数据通常被归类为敏感数据。在这方面,已经提出了各种分类法和概念分类,并开展了标准化活动。不过,这些工作主要针对隐私增强技术的某些子类别,因此缺乏普遍性。这项工作在一个统一的框架内概述了用于生物识别的隐私增强技术的概念。在每个处理步骤中都详细强调了现有概念的关键特性和差异。讨论了现有技术的基本特征和局限性,并将其与数据保护技术和原则联系起来。此外,还介绍了用于生物识别的隐私增强技术的评估方案和方法。本文旨在作为生物识别应用数据保护领域的切入点,面向有经验的研究人员和非专业人员。
{"title":"An Overview of Privacy-Enhancing Technologies in Biometric Recognition","authors":"Pietro Melzi, Christian Rathgeb, Ruben Tolosana, Ruben Vera, Christoph Busch","doi":"10.1145/3664596","DOIUrl":"https://doi.org/10.1145/3664596","url":null,"abstract":"<p>Privacy-enhancing technologies are technologies that implement fundamental data protection principles. With respect to biometric recognition, different types of privacy-enhancing technologies have been introduced for protecting stored biometric data which are generally classified as sensitive. In this regard, various taxonomies and conceptual categorizations have been proposed and standardisation activities have been carried out. However, these efforts have mainly been devoted to certain sub-categories of privacy-enhancing technologies and therefore lack generalization. This work provides an overview of concepts of privacy-enhancing technologies for biometric recognition in a unified framework. Key properties and differences between existing concepts are highlighted in detail at each processing step. Fundamental characteristics and limitations of existing technologies are discussed and related to data protection techniques and principles. Moreover, scenarios and methods for the assessment of privacy-enhancing technologies for biometric recognition are presented. This paper is meant as a point of entry to the field of data protection for biometric recognition applications and is directed towards experienced researchers as well as non-experts.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"104 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141256840","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
Recent Advances for Aerial Object Detection: A Survey 航空物体探测的最新进展:调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-13 DOI: 10.1145/3664598
jiaxu leng, Yongming Ye, Mengjingcheng MO, Chenqiang Gao, Ji Gan, Bin Xiao, Xinbo Gao

Aerial object detection, as object detection in aerial images captured from an overhead perspective, has been widely applied in urban management, industrial inspection, and other aspects. However, the performance of existing aerial object detection algorithms is hindered by variations in object scales and orientations attributed to the aerial perspective. This survey presents a comprehensive review of recent advances in aerial object detection. We start with some basic concepts of aerial object detection and then summarize the five imbalance problems of aerial object detection, including scale imbalance, spatial imbalance, objective imbalance, semantic imbalance, and class imbalance. Moreover, we classify and analyze relevant methods and especially introduce the applications of aerial object detection in practical scenarios. Finally, the performance evaluation is presented on two popular aerial object detection datasets VisDrone-DET and DOTA, and we discuss several future directions that could facilitate the development of aerial object detection.

航空物体检测是指从俯瞰角度拍摄的航空图像中进行物体检测,已被广泛应用于城市管理、工业检测等领域。然而,现有航空物体检测算法的性能受到航空视角导致的物体比例和方向变化的影响。本研究全面回顾了航空物体检测的最新进展。我们首先介绍了空中物体检测的一些基本概念,然后总结了空中物体检测的五个不平衡问题,包括比例不平衡、空间不平衡、目标不平衡、语义不平衡和类别不平衡。此外,我们还对相关方法进行了分类和分析,并特别介绍了航空物体检测在实际场景中的应用。最后,我们对 VisDrone-DET 和 DOTA 这两个流行的航空物体检测数据集进行了性能评估,并讨论了未来促进航空物体检测发展的几个方向。
{"title":"Recent Advances for Aerial Object Detection: A Survey","authors":"jiaxu leng, Yongming Ye, Mengjingcheng MO, Chenqiang Gao, Ji Gan, Bin Xiao, Xinbo Gao","doi":"10.1145/3664598","DOIUrl":"https://doi.org/10.1145/3664598","url":null,"abstract":"<p>Aerial object detection, as object detection in aerial images captured from an overhead perspective, has been widely applied in urban management, industrial inspection, and other aspects. However, the performance of existing aerial object detection algorithms is hindered by variations in object scales and orientations attributed to the aerial perspective. This survey presents a comprehensive review of recent advances in aerial object detection. We start with some basic concepts of aerial object detection and then summarize the five imbalance problems of aerial object detection, including scale imbalance, spatial imbalance, objective imbalance, semantic imbalance, and class imbalance. Moreover, we classify and analyze relevant methods and especially introduce the applications of aerial object detection in practical scenarios. Finally, the performance evaluation is presented on two popular aerial object detection datasets VisDrone-DET and DOTA, and we discuss several future directions that could facilitate the development of aerial object detection.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"59 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140915139","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 Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making 顺序决策的符号、次符号和混合方法综述
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-11 DOI: 10.1145/3663366
Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares

In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this paper reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.

在顺序决策(SDM)领域,历来有两种范式争夺主导地位:自动规划(AP)和强化学习(RL)。本着和解的精神,本文回顾了用于解决序列决策过程(SDP)的自动规划、强化学习和混合方法(如新颖的学习规划技术),重点是它们的知识表示:符号表示、次符号表示或组合表示。此外,它还包括学习 SDP 结构的方法。最后,我们比较了现有方法的优缺点,并得出结论:神经符号人工智能是一种很有前途的 SDM 方法,因为它将 AP 和 RL 与混合知识表示法相结合。
{"title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","authors":"Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares","doi":"10.1145/3663366","DOIUrl":"https://doi.org/10.1145/3663366","url":null,"abstract":"<p>In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this paper reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"191 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140907232","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
Lightweight Deep Learning for Resource-Constrained Environments: A Survey 资源受限环境下的轻量级深度学习:调查
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-05-11 DOI: 10.1145/3657282
Hou-I Liu, Marco Galindo, Hongxia Xie, Lai-Kuan Wong, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.

在过去十年中,深度学习在人工智能的各个领域都占据了主导地位,包括自然语言处理、计算机视觉和生物医学信号处理。虽然模型的准确性有了显著提高,但在手机和微控制器等轻型设备上部署这些模型却受到有限资源的限制。在本研究中,我们为这些设备提供了全面的设计指导,详细介绍了轻量级模型的精心设计、压缩方法和硬件加速策略。这项工作的主要目标是探索在不影响模型准确性的前提下绕过硬件限制的方法和概念。此外,我们还探索了未来轻量级深度学习的两条显著路径:TinyML 和大型语言模型的部署技术。尽管这些路径无疑具有潜力,但它们也提出了巨大的挑战,鼓励对未开发领域进行研究。
{"title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","authors":"Hou-I Liu, Marco Galindo, Hongxia Xie, Lai-Kuan Wong, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng","doi":"10.1145/3657282","DOIUrl":"https://doi.org/10.1145/3657282","url":null,"abstract":"<p>Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.</p>","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"122 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140907237","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