Artificial Intelligence Review最新文献_第3页

ED-Filter: dynamic feature filtering for eating disorder classification ED-Filter：进食障碍分类的动态特征过滤

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-07 DOI: 10.1007/s10462-025-11244-4

Mehdi Naseriparsa, Suku Sukunesan, Zhen Cai, Osama Alfarraj, Amr Tolba, Saba Fathi Rabooki, Feng Xia

{"title":"ED-Filter: dynamic feature filtering for eating disorder classification","authors":"Mehdi Naseriparsa, Suku Sukunesan, Zhen Cai, Osama Alfarraj, Amr Tolba, Saba Fathi Rabooki, Feng Xia","doi":"10.1007/s10462-025-11244-4","DOIUrl":"10.1007/s10462-025-11244-4","url":null,"abstract":"<div><p>Eating disorders (ED) are critical psychiatric problems that have alarmed the mental health community. Mental health professionals are increasingly recognizing the utility of data derived from social media platforms such as Twitter. However, high dimensionality and extensive feature sets of Twitter data present remarkable challenges for ED classification. To overcome these hurdles, we introduce a novel method, an informed branch and bound search technique known as ED-Filter. This strategy significantly improves the drawbacks of conventional feature selection algorithms such as filters and wrappers. ED-Filter iteratively identifies an optimal set of promising features that maximize the eating disorder classification accuracy. In order to adapt to the dynamic nature of Twitter ED data, we enhance the ED-Filter with a hybrid greedy-based deep learning algorithm. This algorithm swiftly identifies sub-optimal features to accommodate the ever-evolving data landscape. Experimental results on Twitter eating disorder data affirm the effectiveness and efficiency of ED-Filter. The method demonstrates significant improvements in classification accuracy and proves its value in eating disorder detection on social media platforms.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11244-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning innovations in CPR: a comprehensive survey on enhanced resuscitation techniques 心肺复苏术中的机器学习创新：对增强复苏技术的全面调查

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-05 DOI: 10.1007/s10462-025-11214-w

Saidul Islam, Gaith Rjoub, Hanae Elmekki, Jamal Bentahar, Witold Pedrycz, Robin Cohen

{"title":"Machine learning innovations in CPR: a comprehensive survey on enhanced resuscitation techniques","authors":"Saidul Islam, Gaith Rjoub, Hanae Elmekki, Jamal Bentahar, Witold Pedrycz, Robin Cohen","doi":"10.1007/s10462-025-11214-w","DOIUrl":"10.1007/s10462-025-11214-w","url":null,"abstract":"<div><p>This survey paper explores the transformative role of Machine Learning (ML) and Artificial Intelligence (AI) in Cardiopulmonary Resuscitation (CPR), marking a paradigm shift from conventional, manually driven resuscitation practices to intelligent, data-driven interventions. It examines the evolution of CPR through the lens of predictive modeling, AI-enhanced devices, and real-time decision-making tools that collectively aim to improve resuscitation outcomes and survival rates. Unlike prior surveys that either focus solely on traditional CPR methods or offer general insights into ML applications in healthcare, this work provides a novel interdisciplinary synthesis tailored specifically to the domain of CPR. It presents a comprehensive taxonomy that classifies ML techniques into four key CPR-related tasks: rhythm analysis, outcome prediction, non-invasive blood pressure and chest compression modeling, and real-time detection of pulse and Return of Spontaneous Circulation (ROSC). The paper critically evaluates emerging ML approaches-including Reinforcement Learning (RL) and transformer-based models-while also addressing real-world implementation barriers such as model interpretability, data limitations, and deployment in high-stakes clinical settings. Furthermore, it highlights the role of eXplainable AI (XAI) in fostering clinical trust and adoption. By bridging the gap between resuscitation science and advanced ML techniques, this survey establishes a structured foundation for future research and practical innovation in ML-enhanced CPR. It offers clear insights, identifies unexplored opportunities, and sets a forward-looking research agenda identifying emerging trends and practical implementation challenges aiming to improve both the reliability and effectiveness of CPR in real-world emergencies.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11214-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adversarial machine learning: a review of methods, tools, and critical industry sectors 对抗性机器学习：对方法、工具和关键行业部门的回顾

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11147-4

Sotiris Pelekis, Thanos Koutroubas, Afroditi Blika, Anastasis Berdelis, Evangelos Karakolis, Christos Ntanos, Evangelos Spiliotis, Dimitris Askounis

{"title":"Adversarial machine learning: a review of methods, tools, and critical industry sectors","authors":"Sotiris Pelekis, Thanos Koutroubas, Afroditi Blika, Anastasis Berdelis, Evangelos Karakolis, Christos Ntanos, Evangelos Spiliotis, Dimitris Askounis","doi":"10.1007/s10462-025-11147-4","DOIUrl":"10.1007/s10462-025-11147-4","url":null,"abstract":"<div><p>The rapid advancement of Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), has produced high-performance models widely used in various applications, ranging from image recognition and chatbots to autonomous driving and smart grid systems. However, security threats arise from the vulnerabilities of ML models to adversarial attacks and data poisoning, posing risks such as system malfunctions and decision errors. Meanwhile, data privacy concerns arise, especially with personal data being used in model training, which can lead to data breaches. This paper surveys the Adversarial Machine Learning (AML) landscape in modern AI systems, while focusing on the dual aspects of robustness and privacy. Initially, we explore adversarial attacks and defenses using comprehensive taxonomies. Subsequently, we investigate robustness benchmarks alongside open-source AML technologies and software tools that ML system stakeholders can use to develop robust AI systems. Lastly, we delve into the landscape of AML in four industry fields –automotive, digital healthcare, electrical power and energy systems (EPES), and Large Language Model (LLM)-based Natural Language Processing (NLP) systems– analyzing attacks, defenses, and evaluation concepts, thereby offering a holistic view of the modern AI-reliant industry and promoting enhanced ML robustness and privacy preservation in the future.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11147-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Overlapping community-based fair influence maximization in social networks under open-source development model algorithm 开源开发模式下社交网络重叠社区公平影响最大化算法

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11210-0

Pengcheng Wei, Bei Yan, Sixing Huang, ZhiHong Zhou

{"title":"Overlapping community-based fair influence maximization in social networks under open-source development model algorithm","authors":"Pengcheng Wei, Bei Yan, Sixing Huang, ZhiHong Zhou","doi":"10.1007/s10462-025-11210-0","DOIUrl":"10.1007/s10462-025-11210-0","url":null,"abstract":"<div><p>The aim of Influence Maximization (IM) in social networks is to identify an optimal subset of users to maximize the spread of influence across the network. Fair Influence Maximization (FIM) develops the IM problem with the aim of equitable distribution of influence across communities and enhancing the fair propagation of information. Among the solutions for FIM, community-based techniques enhance performance by effectively capturing the structural properties and ensuring a more equitable influence spread. However, these techniques often ignore the overlapping nature of communities and suffer from a trade-off between complexity and fairness. With this motivation, this study handles the FIM based on Overlapping Community detection under optimization algorithms (FIMOC). FIMOC includes an overlapping community detection approach that can consider the importance of influential overlapping nodes in communities. Meanwhile, FIMOC uses a non-overlapping and overlapping node selection module based on communities to identify potential candidate nodes. Subsequently, FIMOC uses the Open-Source Development Model Algorithm (ODMA) as an optimization algorithm to identify the set of influential nodes. Our method considers the dynamic and overlapping nature of social communities, ensuring that the influence spread is not only maximized but also equitably distributed across diverse groups. By leveraging real‐world social networks, we demonstrate the effectiveness of our method compared to state-of-the-art methods through extensive experiments. The results show that our method achieves a more balanced influence spread, providing a fairer solution, while also enhancing the overall reach of information dissemination.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11210-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review on clustering algorithms for spatiotemporal seismicity analysis 时空地震活动分析的聚类算法综述

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11229-3

Rahul Kumar Vijay, Satyasai Jagannath Nanda, Ashish Sharma

{"title":"A review on clustering algorithms for spatiotemporal seismicity analysis","authors":"Rahul Kumar Vijay, Satyasai Jagannath Nanda, Ashish Sharma","doi":"10.1007/s10462-025-11229-3","DOIUrl":"10.1007/s10462-025-11229-3","url":null,"abstract":"<div><p>Spatiotemporal seismicity analysis has been conducted for a long time, yet significant effort is still needed to mitigate the adverse effects of earthquakes. Seismicity analysis also encompasses fundamental research into seismic patterns, for understanding the frequency, magnitude, temporal and spatial distribution of seismic events. Over the past few decades, it has been carried out through empirical relations, physics-based approaches, stochastic modeling, various machine learning algorithms, and deep learning algorithms for any given seismically active region. Clustering is an essential aspect of seismicity analysis, making it more complex, difficult, and challenging due to significant deviation from the stochastic phenomenon. In this paper, a comprehensive review of all potential data-driven earthquake clustering algorithms, models, and mechanisms are encapsulated for a variety of applications in seismology. The paper also describes the importance of an earthquake catalog with a short review of the fundamental empirical laws frequently used in statistical seismology. This paper also highlights the problem of seismicity declustering and reviews all the available algorithms to deal with it.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11229-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Review of AI-assisted design of low-carbon cost-effective concrete toward carbon neutrality 人工智能辅助低碳低成本混凝土碳中和设计综述

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11182-1

Soroush Mahjoubi, Rojyar Barhemat, Weina Meng, Yi Bao

{"title":"Review of AI-assisted design of low-carbon cost-effective concrete toward carbon neutrality","authors":"Soroush Mahjoubi, Rojyar Barhemat, Weina Meng, Yi Bao","doi":"10.1007/s10462-025-11182-1","DOIUrl":"10.1007/s10462-025-11182-1","url":null,"abstract":"<div><p>Decarbonizing concrete production is a critical step toward achieving carbon neutrality by 2050. This paper highlights the advancements in artificial intelligence-assisted design of low-carbon cost-effective concrete, focusing on integrating machine learning-based property prediction with multi-objective optimization. Data collection and processing techniques, such as automatic data extraction, artificial data generation, and anomaly detection, are first discussed to address the importance of dataset quality. Strategies that capture physicochemical information of ingredients, including by-product supplementary cementitious materials and recycled aggregates, are then examined to enhance model generalizability. Various machine learning models—from individual regression approaches to heterogeneous ensemble methods—are compared for their predictive accuracy and robustness. Methods for hyperparameter tuning, model evaluation, and interpretation to ensure reliable and interpretable predictions are reviewed. Design optimization approaches are then highlighted, ranging from grid/random searches to more sophisticated gradient-based and metaheuristic algorithms, aimed at minimizing carbon footprint, embodied energy, and cost. Future research avenues encompass (1) application-specific design frameworks that integrate critical objectives—mechanical performance, durability, fresh-state behavior, and time-dependent properties such as creep and shrinkage—tailored to specific structural and environmental requirements; (2) holistic design optimization that simultaneously refines mixture design and structural parameters; and (3) probabilistic approaches to systematically manage uncertainties in materials, structural performance, and loading conditions systematically.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11182-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Parameter-efficient fine-tuning in large language models: a survey of methodologies 大型语言模型中的参数有效微调：方法论综述

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11236-4

Luping Wang, Sheng Chen, Linnan Jiang, Shu Pan, Runze Cai, Sen Yang, Fei Yang

{"title":"Parameter-efficient fine-tuning in large language models: a survey of methodologies","authors":"Luping Wang, Sheng Chen, Linnan Jiang, Shu Pan, Runze Cai, Sen Yang, Fei Yang","doi":"10.1007/s10462-025-11236-4","DOIUrl":"10.1007/s10462-025-11236-4","url":null,"abstract":"<div><p>The large language models, as predicted by scaling law forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the unprecedented scale of their parameters brings significant computational and storage costs. These large language models require substantial computational resources and GPU memory to operate. When adapting large language models to specific downstream tasks, their massive parameter scale poses a significant challenge in fine-tuning on hardware platforms with limited computational power and GPU memory. To address this issue, parameter-efficient fine-tuning (PEFT) offers a practical solution by efficiently adjusting the parameters of large pre-trained models to suit various downstream tasks. Specifically, PEFT adjusts the parameters of pre-trained large language models to adapt to specific tasks or domains, minimizing the introduction of additional parameters and the computational resources required. This review mainly introduces the preliminary knowledge of PEFT, the core ideas and principles of various PEFT algorithms, the applications of PEFT, and potential future research directions. By reading this review, we believe that interested parties can quickly grasp the PEFT methodology, thereby accelerating its development and innovation.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11236-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Refined causal graph structure learning via curvature for brain disease classification 基于曲率的精细因果图结构学习在脑疾病分类中的应用

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11231-9

Falih Gozi Febrinanto, Adonia Simango, Chengpei Xu, Jingjing Zhou, Jiangang Ma, Sonika Tyagi, Feng Xia

{"title":"Refined causal graph structure learning via curvature for brain disease classification","authors":"Falih Gozi Febrinanto, Adonia Simango, Chengpei Xu, Jingjing Zhou, Jiangang Ma, Sonika Tyagi, Feng Xia","doi":"10.1007/s10462-025-11231-9","DOIUrl":"10.1007/s10462-025-11231-9","url":null,"abstract":"<div><p>Graph neural networks (GNNs) have been developed to model the relationship between regions of interest (ROIs) in brains and have shown significant improvement in detecting brain diseases. However, most of these frameworks do not consider the intrinsic relationship of causality factor between brain ROIs, which is arguably more essential to observe cause and effect interaction between signals rather than typical correlation values. We propose a novel framework called Causal Graphs for Brains (CGB) for brain disease classification/detection, which models refined brain networks based on the causal discovery method, transfer entropy, and geometric curvature strategy. CGB unveils causal relationships between ROIs that bring vital information to enhance brain disease classification performance. Furthermore, CGB also performs a graph rewiring through a geometric curvature strategy to refine the generated causal graph to become more expressive and reduce potential information bottlenecks when GNNs model it. Our extensive experiments show that CGB outperforms state-of-the-art methods in classification tasks on brain disease datasets, as measured by average F1 scores.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11231-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Model-agnostic explainable artificial intelligence methods in finance: a systematic review, recent developments, limitations, challenges and future directions 金融中模型不可知的可解释人工智能方法：系统回顾、最新发展、限制、挑战和未来方向

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11215-9

Farhina Sardar Khan, Syed Shahid Mazhar, Kashif Mazhar, Dhoha A. AlSaleh, Amir Mazhar

{"title":"Model-agnostic explainable artificial intelligence methods in finance: a systematic review, recent developments, limitations, challenges and future directions","authors":"Farhina Sardar Khan, Syed Shahid Mazhar, Kashif Mazhar, Dhoha A. AlSaleh, Amir Mazhar","doi":"10.1007/s10462-025-11215-9","DOIUrl":"10.1007/s10462-025-11215-9","url":null,"abstract":"<div><p>The increasing integration of Artificial Intelligence (AI) and Machine Learning (ML)—algorithms that enable computers to identify patterns from data—in financial applications has significantly improved predictive capabilities in areas such as credit scoring, fraud detection, portfolio management, and risk assessment. Despite these advancements, the opaque, “black box” nature of many AI and ML models raises critical concerns related to transparency, trust, and regulatory compliance. Explainable Artificial Intelligence (XAI) aims to address these issues by providing interpretable and transparent decision-making processes. This study systematically reviews Model-Agnostic Explainable AI techniques, which can be applied across different types of ML models in finance, to evaluate their effectiveness, scalability, and practical applicability. Through analysis of 150 peer-reviewed studies, the paper identifies key challenges, such as balancing interpretability with predictive accuracy, managing computational complexity, and meeting regulatory requirements. The review highlights emerging trends toward hybrid models that combine powerful ML algorithms with interpretability techniques, real-time explanations suitable for dynamic financial markets, and XAI frameworks explicitly designed to align with regulatory standards. The study concludes by outlining specific future research directions, including the development of computationally efficient explainability methods, regulatory-compliant frameworks, and ethical AI solutions to ensure transparent and accountable financial decision-making.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11215-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring privacy mechanisms and metrics in federated learning 探索联邦学习中的隐私机制和度量

IF 10.7 2区计算机科学

Artificial Intelligence Review Pub Date : 2025-05-03 DOI: 10.1007/s10462-025-11170-5

Dhanya Shenoy, Radhakrishna Bhat, Krishna Prakasha K

{"title":"Exploring privacy mechanisms and metrics in federated learning","authors":"Dhanya Shenoy, Radhakrishna Bhat, Krishna Prakasha K","doi":"10.1007/s10462-025-11170-5","DOIUrl":"10.1007/s10462-025-11170-5","url":null,"abstract":"<div><p>The federated learning (FL) principle ensures multiple clients jointly develop a machine learning model without exchanging their local data. Various government enacted prohibition policies on data exchange between organizations have led to the need for privacy-preserved federated learning. Many industries have cultivated this idea of model development through federated learning to enhance performance and accuracy. This paper offers a detailed overview of the background of FL, highlighting existing aggregation algorithms, frameworks, implementation aspects, and dataset repositories, establishing itself as an essential reference for researchers in the field. The paper thoroughly reviews existing centralized and decentralized FL approaches proposed in the literature and gives an overview about the methodology, privacy techniques implemented and limitations to guide other researchers to advance their research in the field of federated learning. The paper discusses the critical role of privacy-enhancing technologies like differential privacy (DP), homomorphic encryption (HE), and secure multiparty computation (SMPC) in federated learning highlighting their effectiveness in safeguarding sensitive data while optimizing the balance between privacy, communication efficiency, and computational cost. The paper explores the applications of federated learning in privacy-sensitive areas like natural language processing (NLP), healthcare, and Internet of Things (IoT) with edge computing. We believe our work provides a novel addition by identifying privacy evaluation metrics and spotlighting the measures in terms of data privacy and correctness, communication cost, computational cost and scalability. Furthermore, it identifies emerging challenges and suggests promising research directions in the federated learning domain.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 8","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11170-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0