{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T10:07:29Z","timestamp":1775210849467,"version":"3.50.1"},"reference-count":114,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007637","name":"German University in Cairo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007637","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Federated Learning (FL) enables collaborative model training without exposing sensitive data, making it a cornerstone for privacy-aware AI. However, bringing FL from theory to practice in multi-tier architectures that contain hierarchical edge-fog-cloud systems remains difficult, challenged by security vulnerabilities, resource constraints, and system heterogeneity. This paper reviews secure and adaptive optimization techniques that address these challenges in hierarchical environments. We focus on three main areas: (1) security-enhanced FL, covering threat models, adversarial attacks, and defenses tailored to layered architectures; (2) adaptive optimization, including dynamic client selection, resource-aware aggregation, and context-sensitive privacy management; and (3) systems integration, examining architectural designs, communication protocols, and orchestration methods for scalable deployment. By synthesizing recent work, the survey highlights trade-offs between privacy, performance, and scalability, and proposes a taxonomy of current challenges and solutions. It also evaluates approaches to trustworthiness in FL, including fairness, accountability, and robustness, while considering practical issues such as regulation, benchmarking, and deployment constraints. The paper concludes with open research directions, emphasizing the need for secure, adaptive, and production-ready FL systems.<\/jats:p>","DOI":"10.1007\/s44443-026-00510-2","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T10:30:44Z","timestamp":1774607444000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Review on federated optimization in multi-tier architectures"],"prefix":"10.1007","volume":"38","author":[{"given":"Dinah","family":"Waref","sequence":"first","affiliation":[]},{"given":"Yomna","family":"Alayary","sequence":"additional","affiliation":[]},{"given":"Mohamed A.","family":"Abd El Ghany","sequence":"additional","affiliation":[]},{"given":"Mohammed A.-M.","family":"Salem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"510_CR1","unstructured":"Akinsiku AM (2025) A comprehensive survey of federated learning approaches for privacy-preserving machine learning. Tech-Sphere Journal for Pure and Applied Sciences 2(1)"},{"issue":"1","key":"510_CR2","first-page":"1","volume":"12","author":"RZ Alshamasi","year":"2025","unstructured":"Alshamasi RZ, Ibrahim DM (2025) Federated intelligence for smart grids: a comprehensive review of security and privacy strategies. J Electr Syst Inf Technol 12(1):1\u201326","journal-title":"J Electr Syst Inf Technol"},{"issue":"17","key":"510_CR3","doi-asserted-by":"publisher","first-page":"5492","DOI":"10.3390\/s24175492","volume":"24","author":"H Alshede","year":"2024","unstructured":"Alshede H, Jambi K, Nassef L, Alowidi N, Fadel E (2024) Fedavg-p: Performance-based hierarchical federated learning-based anomaly detection system aggregation strategy for advanced metering infrastructure. Sensors (Basel Switzerland) 24(17):5492","journal-title":"Sensors (Basel Switzerland)"},{"issue":"20","key":"510_CR4","doi-asserted-by":"publisher","first-page":"4364","DOI":"10.3390\/electronics12204364","volume":"12","author":"T An","year":"2023","unstructured":"An T, Ma L, Wang W, Yang Y, Wang J, Chen Y (2023) Consideration of fedprox in privacy protection. Electronics 12(20):4364","journal-title":"Electronics"},{"issue":"5","key":"510_CR5","first-page":"1333","volume":"13","author":"Y Aono","year":"2017","unstructured":"Aono Y, Hayashi T, Wang L, Moriai S et al (2017) Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans Inf Forensics Secur 13(5):1333\u20131345","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"510_CR6","unstructured":"Arazzi M, Cihangiroglu M, Nocera A (2025) Privacy preserving and robust aggregation for cross-silo federated learning in non-iid settings. arXiv:2503.04451"},{"issue":"17","key":"510_CR7","doi-asserted-by":"publisher","first-page":"7358","DOI":"10.3390\/s23177358","volume":"23","author":"M Asad","year":"2023","unstructured":"Asad M, Shaukat S, Hu D, Wang Z, Javanmardi E, Nakazato J, Tsukada M (2023) Limitations and future aspects of communication costs in federated learning: A survey. Sensors 23(17):7358","journal-title":"Sensors"},{"key":"510_CR8","unstructured":"Baumgart GA, Shin J, Payani A, Lee M, Kompella RR (2024) Not all federated learning algorithms are created equal: A performance evaluation study. arXiv:2403.17287"},{"issue":"4","key":"510_CR9","doi-asserted-by":"publisher","first-page":"124","DOI":"10.3390\/computers14040124","volume":"14","author":"MRA Berkani","year":"2025","unstructured":"Berkani MRA, Chouchane A, Himeur Y, Ouamane A, Miniaoui S, Atalla S, Mansoor W, Al-Ahmad H (2025) Advances in federated learning: Applications and challenges in smart building environments and beyond. Computers 14(4):124","journal-title":"Computers"},{"key":"510_CR10","unstructured":"Bhagoji AN, Chakraborty S, Mittal P, Calo S (2019) Analyzing federated learning through an adversarial lens. In: International conference on machine learning, pp 634\u2013643. PMLR"},{"key":"510_CR11","unstructured":"Blanchard P, Mhamdi EME, Guerraoui R, Stainer J (2017) Byzantine-tolerant machine learning. arXiv:1703.02757"},{"key":"510_CR12","unstructured":"Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage D, Segal A, Seth K (2016) Practical secure aggregation for federated learning on user-held data. arXiv:1611.04482"},{"key":"510_CR13","doi-asserted-by":"crossref","unstructured":"Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage D, Segal A, Seth K (2017) Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security, pp 1175\u20131191","DOI":"10.1145\/3133956.3133982"},{"key":"510_CR14","doi-asserted-by":"crossref","unstructured":"Bonomi F, Milito R, Zhu J, Addepalli S (2012) Fog computing and its role in the internet of things. In: Proceedings of the first edition of the MCC workshop on mobile cloud computing, pp 13\u201316","DOI":"10.1145\/2342509.2342513"},{"key":"510_CR15","doi-asserted-by":"crossref","unstructured":"Bouaziz S, Benmeziane H, Imine Y, Hamdad L, Niar S, Ouarnoughi H (2023) Flash-rl: Federated learning addressing system and static heterogeneity using reinforcement learning. In: 2023 IEEE 41st international conference on computer design (ICCD), pp 444\u2013447 . IEEE","DOI":"10.1109\/ICCD58817.2023.00074"},{"key":"510_CR16","unstructured":"Caldas S, Duddu S.M.K, Wu P, Li T, Kone\u010dn\u1ef3 J, McMahan H.B, Smith V, Talwalkar A (2018) Leaf: A benchmark for federated settings. arXiv:1812.01097"},{"key":"510_CR17","doi-asserted-by":"crossref","unstructured":"Cao X, Fang M, Liu J, Gong NZ (2020) Fltrust: Byzantine-robust federated learning via trust bootstrapping. arXiv:2012.13995","DOI":"10.14722\/ndss.2021.24434"},{"issue":"3","key":"510_CR18","doi-asserted-by":"publisher","first-page":"3397","DOI":"10.1007\/s11042-021-11219-x","volume":"81","author":"FE Casado","year":"2022","unstructured":"Casado FE, Lema D, Criado MF, Iglesias R, Regueiro CV, Barro S (2022) Concept drift detection and adaptation for federated and continual learning. Multimed Tools Appl 81(3):3397\u20133419","journal-title":"Multimed Tools Appl"},{"key":"510_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.908814","volume":"13","author":"A Chen","year":"2022","unstructured":"Chen A, Fu Y, Sha Z, Lu G (2022) An emd-based adaptive client selection algorithm for federated learning in heterogeneous data scenarios. Front Plant Sci 13:908814","journal-title":"Front Plant Sci"},{"issue":"12","key":"510_CR20","first-page":"1","volume":"56","author":"J Chen","year":"2024","unstructured":"Chen J, Yan H, Liu Z, Zhang M, Xiong H, Yu S (2024) When federated learning meets privacy-preserving computation. ACM Comput Surv 56(12):1\u201336","journal-title":"ACM Comput Surv"},{"key":"510_CR21","doi-asserted-by":"crossref","unstructured":"Chen Y, Chai Z, Cheng Y, Rangwala H (2021) Asynchronous federated learning for sensor data with concept drift. In: 2021 IEEE international conference on big data (Big Data), pp 4822\u20134831 . IEEE","DOI":"10.1109\/BigData52589.2021.9671924"},{"key":"510_CR22","doi-asserted-by":"crossref","unstructured":"Chen D, Hu J, Tan VJ, Wei X, Wu E (2023) Elastic aggregation for federated optimization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12187\u201312197","DOI":"10.1109\/CVPR52729.2023.01173"},{"key":"510_CR23","doi-asserted-by":"crossref","unstructured":"Chen Y, Wu C, Du Z, Lin Y, Djahel S, Zhong L (2024) Hier-fedmeta: A hierarchical federated meta-learning framework for personalized and efficient iov systems. In: 2024 IEEE 99th vehicular technology conference (VTC2024-Spring), pp 1\u20135 . IEEE","DOI":"10.1109\/VTC2024-Spring62846.2024.10683124"},{"key":"510_CR24","unstructured":"Cho Y.J, Jhunjhunwala D, Li T, Smith V, Joshi G (2022) To federate or not to federate: Incentivizing client participation in federated learning. In: Workshop on federated learning: recent advances and new challenges (in Conjunction with NeurIPS 2022)"},{"key":"510_CR25","unstructured":"Cho YJ, Wang J, Joshi G (2022) Towards understanding biased client selection in federated learning. In: International conference on artificial intelligence and statistics, pp 10351\u201310375. PMLR"},{"key":"510_CR26","unstructured":"Chuan WC, Manickam S, Ashraf E, Karuppayah S et al (2025) Challenges and opportunities in fog computing scheduling: a literature review. IEEE Access"},{"key":"510_CR27","doi-asserted-by":"crossref","unstructured":"Daly K, Eichner H, Kairouz P, McMahan HB, Ramage D, Xu Z (2024) Federated learning in practice: reflections and projections. In: 2024 IEEE 6th international conference on trust, privacy and security in intelligent systems, and applications (TPS-iSA), pp 148\u2013156 . IEEE","DOI":"10.1109\/TPS-ISA62245.2024.00026"},{"key":"510_CR28","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.7717\/peerj-cs.1445","volume":"9","author":"JJ Damanik","year":"2023","unstructured":"Damanik JJ, Lim MC, Jeong H-M, Kim H-Y, Choi H-L (2023) Consensus-based clustering and data aggregation in decentralized network of multi-agent systems. PeerJ Computer Science 9:1445","journal-title":"PeerJ Computer Science"},{"key":"510_CR29","unstructured":"Dao T, Nguyen DT, Doan KD, Wong K-S (2025) Backfed: An efficient & standardized benchmark suite for backdoor attacks in federated learning. arXiv:2507.04903"},{"key":"510_CR30","doi-asserted-by":"crossref","unstructured":"Dwork C, Roth A et al (2014) The algorithmic foundations of differential privacy. Foundations and Trends\u00aein Theoretical Comput Sci 9(3-4):211\u2013407","DOI":"10.1561\/0400000042"},{"key":"510_CR31","doi-asserted-by":"crossref","unstructured":"Erlingsson \u00da, Feldman V, Mironov I, Raghunathan A, Talwar K, Thakurta A (2019) Amplification by shuffling: From local to central differential privacy via anonymity. In: Proceedings of the thirtieth annual ACM-SIAM symposium on discrete algorithms, pp 2468\u20132479. SIAM","DOI":"10.1137\/1.9781611975482.151"},{"key":"510_CR32","unstructured":"Fallah A, Mokhtari A, Ozdaglar A (2020) Personalized federated learning: A meta-learning approach. arXiv:2002.07948"},{"issue":"2","key":"510_CR33","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s40747-024-01664-0","volume":"11","author":"Y Feng","year":"2025","unstructured":"Feng Y, Guo Y, Hou Y, Wu Y, Lao M, Yu T, Liu G (2025) A survey of security threats in federated learning. Complex & Intell Syst 11(2):165","journal-title":"Complex & Intell Syst"},{"key":"510_CR34","doi-asserted-by":"crossref","unstructured":"Feng C, Huertas\u00a0Celdran A, S\u00e1nchez\u00a0S\u00e1nchez PM, Zumtaugwalda G, Burkhard\u00a0Stille L, Bovet G, Stiller B (2025) Assessing the sustainability and trustworthiness of federated learning models. Lynn and Bovet, G\u00e9r\u00f4me and Stiller, Burkhard, Assessing the Sustainability and Trustworthiness of Federated Learning Models","DOI":"10.2139\/ssrn.5132762"},{"key":"510_CR35","unstructured":"Fung C, Yoon CJ, Beschastnikh I (2020) The limitations of federated learning in sybil settings. In: 23rd International symposium on research in attacks, intrusions and defenses (RAID 2020), pp 301\u2013316"},{"key":"510_CR36","unstructured":"Gallus S, Johnson A, Desai P, Lee M (2025) Enhancing federated learning efficiency via multi-objective optimization"},{"key":"510_CR37","doi-asserted-by":"crossref","unstructured":"Gao J, Li Y, Zhao Y, Campbell B (2024) H-fedsn: Personalized sparse networks for efficient and accurate hierarchical federated learning for iot applications. arXiv:2412.06210","DOI":"10.1109\/ITW61385.2024.10806940"},{"key":"510_CR38","doi-asserted-by":"crossref","unstructured":"Gao W, Tavallaie O, Chen S, Zomaya A (2024) Federated learning as a service for hierarchical edge networks with heterogeneous models. In: International conference on service-oriented computing, pp 85\u201399. Springer","DOI":"10.1007\/978-981-96-0805-8_6"},{"key":"510_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114004","volume":"326","author":"M Garc\u00eda-M\u00e1rquez","year":"2025","unstructured":"Garc\u00eda-M\u00e1rquez M, Rodr\u00edguez-Barroso N, Luz\u00f3n MV, Herrera F (2025) Improving ($$\\alpha $$, f)-byzantine resilience in federated learning via layerwise aggregation and cosine distance. Knowl-Based Syst 326:114004. https:\/\/doi.org\/10.1016\/j.knosys.2025.114004","journal-title":"Knowl-Based Syst"},{"key":"510_CR40","unstructured":"Geyer RC, Klein T, Nabi M (2017) Differentially private federated learning: A client level perspective. arXiv:1712.07557"},{"key":"510_CR41","unstructured":"Gupta S (2025) Federated learning: Advancing privacy-preserving machine learning at scale"},{"key":"510_CR42","doi-asserted-by":"publisher","unstructured":"Hao F, Zhi T, Gu T, Bao X (2025) Toward customized model discrepancies in personalized federated learning on non-IID data. Knowl. Based Syst. 330:114522. ISSN 0950-7051. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705125015618, https:\/\/doi.org\/10.1016\/j.knosys.2025.114522","DOI":"10.1016\/j.knosys.2025.114522"},{"key":"510_CR43","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.7717\/peerj-cs.2993","volume":"11","author":"C-A Hatfaludi","year":"2025","unstructured":"Hatfaludi C-A, Serban A (2025) Foundational models and federated learning: survey, taxonomy, challenges and practical insights. PeerJ Comput Sci 11:2993","journal-title":"PeerJ Comput Sci"},{"key":"510_CR44","doi-asserted-by":"crossref","unstructured":"Hsu C-F, Huang J-L, Liu F-H, Chang M-C, Chen W-C (2022) Fedtrust: Towards building secure robust and trustworthy moderators for federated learning. In: 2022 IEEE 5th international conference on multimedia information processing and retrieval (MIPR), pp 318\u2013323 . IEEE","DOI":"10.1109\/MIPR54900.2022.00063"},{"issue":"1","key":"510_CR45","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TDSC.2024.3392424","volume":"22","author":"C Hu","year":"2024","unstructured":"Hu C, Li B (2024) Maskcrypt: Federated learning with selective homomorphic encryption. IEEE Trans Dependable Secure Comput 22(1):221\u2013233","journal-title":"IEEE Trans Dependable Secure Comput"},{"issue":"4","key":"510_CR46","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1109\/TNSE.2022.3169117","volume":"9","author":"Z Hu","year":"2022","unstructured":"Hu Z, Shaloudegi K, Zhang G, Yu Y (2022) Federated learning meets multi-objective optimization. IEEE Trans Netw Sci Eng 9(4):2039\u20132051","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"510_CR47","doi-asserted-by":"crossref","unstructured":"Huang C, Chen X, Zhang Y, Wang H (2024) Fedcrl: Personalized federated learning with contrastive shared representations for label heterogeneity in non-iid data. arXiv:2404.17916","DOI":"10.1109\/TCYB.2025.3599370"},{"key":"510_CR48","unstructured":"Huff W, Pinyoanuntapong P, Ravikumar B, Hao F, Lee M, Wang P, Chen C (2023) Dha-fl: Enabling efficient and effective aiot via decentralized hierarchical asynchronous federated learning. MLSys-RCLWN 2023"},{"issue":"10","key":"510_CR49","doi-asserted-by":"publisher","first-page":"14205","DOI":"10.1109\/TNNLS.2023.3275634","volume":"35","author":"C Huo","year":"2023","unstructured":"Huo C, He D, Liang C, Jin D, Qiu T, Wu L (2023) Trustgnn: Graph neural network-based trust evaluation via learnable propagative and composable nature. IEEE Trans Neural Netw and Learn Syst 35(10):14205\u201314217","journal-title":"IEEE Trans Neural Netw and Learn Syst"},{"key":"510_CR50","doi-asserted-by":"crossref","unstructured":"Ilhan F, Su G, Liu L (2023) Scalefl: Resource-adaptive federated learning with heterogeneous clients. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 24532\u201324541","DOI":"10.1109\/CVPR52729.2023.02350"},{"key":"510_CR51","doi-asserted-by":"crossref","unstructured":"Jia R, Xie W, Lei J, Li Y (2024) Adaptive hierarchical aggregation for federated object detection. In: Proceedings of the 32nd ACM international conference on multimedia, pp 3732\u20133740","DOI":"10.1145\/3664647.3681158"},{"key":"510_CR52","doi-asserted-by":"crossref","unstructured":"Kairouz P, McMahan HB, Avent B, Bellet A, Bennis M, Bhagoji AN, Bonawitz K, Charles Z, Cormode G, Cummings R et al (2021) Advances and open problems in federated learning. Foundations and trends\u00aein machine learning 14(1-2):1\u2013210","DOI":"10.1561\/2200000083"},{"issue":"6","key":"510_CR53","doi-asserted-by":"publisher","first-page":"10700","DOI":"10.1109\/JIOT.2019.2940820","volume":"6","author":"J Kang","year":"2019","unstructured":"Kang J, Xiong Z, Niyato D, Xie S, Zhang J (2019) Incentive mechanism for reliable federated learning: A joint optimization approach to combining reputation and contract theory. IEEE Internet Things J 6(6):10700\u201310714","journal-title":"IEEE Internet Things J"},{"key":"510_CR54","unstructured":"Karimireddy SP, Kale S, Mohri M, Reddi S, Stich S, Suresh AT (2020) Scaffold: Stochastic controlled averaging for federated learning. In: International conference on machine learning, pp 5132\u20135143. PMLR"},{"key":"510_CR55","first-page":"63","volume-title":"A review of secure gradient compression techniques for federated learning in the internet of medical things","author":"T Kelly","year":"2025","unstructured":"Kelly T, Alhonainy A, Rao P (2025) A review of secure gradient compression techniques for federated learning in the internet of medical things. Towards Privacy-Preserving Distributed AI, Federated Learning Systems, pp 63\u201385"},{"key":"510_CR56","doi-asserted-by":"crossref","unstructured":"Khan N, Nisar S, Khan MA, Rehman YAU, Noor F, Barb G (2025) Optimizing federated learning with aggregation strategies: A comprehensive survey. IEEE Open J Comput Soc","DOI":"10.1109\/OJCS.2025.3590102"},{"key":"510_CR57","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V (2020) Federated optimization in heterogeneous networks. Proc Mach Learn Syst 2:429\u2013450","journal-title":"Proc Mach Learn Syst"},{"key":"510_CR58","doi-asserted-by":"crossref","unstructured":"Li Y, Guo Z, Yang N, Chen H, Yuan D, Ding W (2025) Threats and defenses in the federated learning life cycle: a comprehensive survey and challenges. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2025.3563537"},{"key":"510_CR59","doi-asserted-by":"crossref","unstructured":"Li Q, He B, Song D (2021) Model-contrastive federated learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10713\u201310722","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"510_CR60","unstructured":"Li X, Huang K, Yang W, Wang S, Zhang Z (2019) On the convergence of fedavg on non-iid data. arXiv:1907.02189"},{"key":"510_CR61","unstructured":"Li T, Hu S, Beirami A, Smith V (2021) Ditto: Fair and robust federated learning through personalization. In: International conference on machine learning, pp 6357\u20136368. PMLR"},{"key":"510_CR62","doi-asserted-by":"crossref","unstructured":"Li Q, Li X, Zhou L, Yan X (2024) Adafl: Adaptive client selection and dynamic contribution evaluation for efficient federated learning. In: ICASSP 2024-2024 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 6645\u20136649 . IEEE","DOI":"10.1109\/ICASSP48485.2024.10447356"},{"issue":"3","key":"510_CR63","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1109\/TPDS.2021.3096076","volume":"33","author":"WYB Lim","year":"2021","unstructured":"Lim WYB, Ng JS, Xiong Z, Jin J, Zhang Y, Niyato D, Leung C, Miao C (2021) Decentralized edge intelligence: A dynamic resource allocation framework for hierarchical federated learning. IEEE Trans Parallel Distrib Syst 33(3):536\u2013550","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"510_CR64","doi-asserted-by":"crossref","unstructured":"Liu G, Lin W, Huang T, Shi F, Wu W, Shen L (2025) Adaptivefl: Communication-adaptive federated learning under dynamic bandwidth. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2025.3560656"},{"key":"510_CR65","doi-asserted-by":"crossref","unstructured":"Liu L, Zhang J, Song S, Letaief KB (2020) Client-edge-cloud hierarchical federated learning. In: ICC 2020-2020 IEEE international conference on communications (ICC), pp 1\u20136 . IEEE","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"510_CR66","doi-asserted-by":"crossref","unstructured":"Luo T, Wang J, Yan Z, Gelenbe E (2025) Graph neural networks for trust evaluation: Criteria, state-of-the-art, and future directions. IEEE Netw","DOI":"10.1109\/MNET.2025.3551068"},{"key":"510_CR67","doi-asserted-by":"crossref","unstructured":"Lyu L, Yu H, Yang Q (2020) Threats to federated learning: A survey. arXiv:2003.02133","DOI":"10.1007\/978-3-030-63076-8_1"},{"key":"510_CR68","unstructured":"Malekijoo A, Fadaeieslam MJ, Malekijou H, Homayounfar M, Alizadeh-Shabdiz F, Rawassizadeh R (2021) Fedzip: A compression framework for communication-efficient federated learning. arXiv:2102.01593"},{"issue":"4","key":"510_CR69","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1109\/COMST.2017.2745201","volume":"19","author":"Y Mao","year":"2017","unstructured":"Mao Y, You C, Zhang J, Huang K, Letaief KB (2017) A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials 19(4):2322\u20132358","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"510_CR70","unstructured":"Mavromatis I, De\u00a0Feo S, Khan A (2024) Flame: Adaptive and reactive concept drift mitigation for federated learning deployments. arXiv:2410.01386"},{"key":"510_CR71","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, pp 1273\u20131282 . PMLR"},{"key":"510_CR72","first-page":"4270","volume":"35","author":"Y Mei","year":"2022","unstructured":"Mei Y, Guo P, Zhou M (2022) Patel V Resource-adaptive federated learning with all-in-one neural composition. Adv Neural Inf Process Syst 35:4270\u20134284","journal-title":"Adv Neural Inf Process Syst"},{"key":"510_CR73","first-page":"14606","volume":"34","author":"A Mitra","year":"2021","unstructured":"Mitra A, Jaafar R, Pappas GJ, Hassani H (2021) Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients. Adv Neural Inf Process Syst 34:14606\u201314619","journal-title":"Adv Neural Inf Process Syst"},{"key":"510_CR74","doi-asserted-by":"crossref","unstructured":"Mitra A, Hassani H, Pappas GJ (2021) Online federated learning. In: 2021 60th IEEE conference on decision and control (CDC), pp 4083\u20134090 . IEEE","DOI":"10.1109\/CDC45484.2021.9683589"},{"key":"510_CR75","unstructured":"Muhebwa A, Selialia K, Anwar F, Osman KK (2025) Kuramoto-fedavg: Using synchronization dynamics to improve federated learning optimization under statistical heterogeneity. arXiv:2505.19605"},{"issue":"2","key":"510_CR76","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s41060-024-00691-x","volume":"19","author":"GS Nariman","year":"2025","unstructured":"Nariman GS, Hamarashid HK (2025) Communication overhead reduction in federated learning: a review. Int J Data Scie Anal 19(2):185\u2013216","journal-title":"Int J Data Scie Anal"},{"key":"510_CR77","unstructured":"Ning Z, Tian C, Xiao M, Fan W, Wang P, Li L, Wang P, Zhou Y (2024) Fedgcs: A generative framework for efficient client selection in federated learning via gradient-based optimization. arXiv:2405.06312"},{"key":"510_CR78","unstructured":"Orca Security (2024) 2024 State of AI Security Report. https:\/\/orca.security\/lp\/2024-state-of-ai-security-report\/. Accessed: [Current Date, e.g., 21 July 2025]"},{"key":"510_CR79","doi-asserted-by":"crossref","unstructured":"Pais V, Rao S, Muniyal B (2025) Strategies for reducing the communication and computation costs in cross-silo federated learning: A comprehensive review. IEEE Access","DOI":"10.1109\/ACCESS.2025.3573933"},{"key":"510_CR80","unstructured":"Panchal K, Choudhary S, Mitra S, Mukherjee K, Sarkhel S, Mitra S, Guan H (2023) Flash: Concept drift adaptation in federated learning. In: International conference on machine learning, pp 26931\u201326962. PMLR"},{"key":"510_CR81","unstructured":"Pearcy S (2025) Hiddenlayer Ai Threat Landscape Report reveals AI breaches on The rise . https:\/\/hiddenlayer.com\/innovation-hub\/hiddenlayer-ai-threat-landscape-report-reveals-ai-breaches-on-the-rise\/"},{"key":"510_CR82","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1016\/j.future.2023.09.008","volume":"150","author":"P Qi","year":"2024","unstructured":"Qi P, Chiaro D, Guzzo A, Ianni M, Fortino G, Piccialli F (2024) Model aggregation techniques in federated learning: A comprehensive survey. Futur Gener Comput Syst 150:272\u2013293","journal-title":"Futur Gener Comput Syst"},{"key":"510_CR83","doi-asserted-by":"crossref","unstructured":"Qi J, Zhou Q, Lei L, Zheng K (2021) Federated reinforcement learning: Techniques, applications, and open challenges. arXiv:2108.11887","DOI":"10.20517\/ir.2021.02"},{"key":"510_CR84","unstructured":"Rahulamathavan Y, Herath C, Liu X, Lambotharan S, Maple C (2023) Fhefl: Fully homomorphic encryption friendly privacy-preserving federated learning with byzantine users. arXiv:2306.05112"},{"key":"510_CR85","unstructured":"Reddi S, Charles Z, Zaheer M, Garrett Z, Rush K, Kone\u010dn\u1ef3 J, Kumar S, McMahan HB(2020) Adaptive federated optimization. arXiv:2003.00295"},{"key":"510_CR86","unstructured":"Roth H, Zephyr M, Harouni A (2021) Federated learning with homomorphic encryption. NVIDIA\u2122 Developer Blog"},{"key":"510_CR87","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122874","volume":"243","author":"F Sabah","year":"2024","unstructured":"Sabah F, Chen Y, Yang Z, Azam M, Ahmad N, Sarwar R (2024) Model optimization techniques in personalized federated learning: A survey. Expert Syst Appl 243:122874","journal-title":"Expert Syst Appl"},{"key":"510_CR88","unstructured":"Salazar T, Gama J, Araujo H, Abreu PH (2024) Unveiling group-specific distributed concept drift: A fairness imperative in federated learning. arXiv:2402.07586"},{"key":"510_CR89","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.future.2023.10.013","volume":"152","author":"PMS S\u00e1nchez","year":"2024","unstructured":"S\u00e1nchez PMS, Celdr\u00e1n AH, Xie N, Bovet G, P\u00e9rez GM, Stiller B (2024) Federatedtrust: A solution for trustworthy federated learning. Future Gen Comput Syst 152:83\u201398","journal-title":"Future Gen Comput Syst"},{"issue":"1","key":"510_CR90","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2017.9","volume":"50","author":"M Satyanarayanan","year":"2017","unstructured":"Satyanarayanan M (2017) The emergence of edge computing. Computer 50(1):30\u201339","journal-title":"Computer"},{"key":"510_CR91","unstructured":"Sen M, Aparna S, Agarwal R, Mohan CK (2025) Overcoming challenges of partial client participation in federated learning: A comprehensive review. arXiv:2506.02887"},{"key":"510_CR92","unstructured":"Seo J, Catak FO, Rong C (2025) Understanding federated learning from iid to non-iid dataset: An experimental study. arXiv:2502.00182"},{"key":"510_CR93","doi-asserted-by":"crossref","unstructured":"Seo S, Kim J, Kim G, Han B (2024) Relaxed contrastive learning for federated learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12279\u201312288","DOI":"10.1109\/CVPR52733.2024.01167"},{"key":"510_CR94","unstructured":"Shamsian A, Navon A, Fetaya E, Chechik G (2021) Personalized federated learning using hypernetworks. In: International conference on machine learning, pp 9489\u20139502 . PMLR"},{"issue":"5","key":"510_CR95","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","volume":"3","author":"W Shi","year":"2016","unstructured":"Shi W, Cao J, Zhang Q, Li Y, Xu L (2016) Edge computing: Vision and challenges. IEEE Internet Things J 3(5):637\u2013646","journal-title":"IEEE Internet Things J"},{"key":"510_CR96","unstructured":"Szel\u0105g JK, Chin J-J, Yip S-C (2025) Adaptive adversaries in byzantine-robust federated learning: A survey. Cryptology ePrint Archive"},{"key":"510_CR97","first-page":"19332","volume":"35","author":"Y Tan","year":"2022","unstructured":"Tan Y, Long G, Ma J, Liu L, Zhou T, Jiang J (2022) Federated learning from pre-trained models: A contrastive learning approach. Adv Neural Inf Process Syst 35:19332\u201319344","journal-title":"Adv Neural Inf Process Syst"},{"issue":"14","key":"510_CR98","doi-asserted-by":"publisher","first-page":"6518","DOI":"10.3390\/s23146518","volume":"23","author":"J Tang","year":"2023","unstructured":"Tang J, Ding X, Hu D, Guo B, Shen Y, Ma P, Jiang Y (2023) Fedrad: Heterogeneous federated learning via relational adaptive distillation. Sensors 23(14):6518","journal-title":"Sensors"},{"key":"510_CR99","doi-asserted-by":"crossref","unstructured":"Tariq A, Serhani MA, Sallabi FM, Barka ES, Qayyum T, Khater HM, Shuaib KA (2024) Trustworthy federated learning: A comprehensive review, architecture, key challenges, and future research prospects. IEEE Open Journal of the Communications Society","DOI":"10.1109\/OJCOMS.2024.3438264"},{"key":"510_CR100","doi-asserted-by":"crossref","unstructured":"Thomas J, Saile F, Fischer M, Kaaser D, Schulte S (2025) Adaption via selection: on client selection to counter concept drift in federated learning. In: European conference on service-oriented and cloud computing, pp 3\u201317. Springer","DOI":"10.1007\/978-3-031-84617-5_1"},{"issue":"10","key":"510_CR101","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3727643","volume":"57","author":"MP Uddin","year":"2025","unstructured":"Uddin MP, Xiang Y, Hasan M, Bai J, Zhao Y, Gao L (2025) A systematic literature review of robust federated learning: Issues, solutions, and future research directions. ACM Comput Surv 57(10):1\u201362","journal-title":"ACM Comput Surv"},{"key":"510_CR102","unstructured":"Wang Z, Hu Q (2021) Blockchain-based federated learning: A comprehensive survey pp 1\u201318. arXiv:2110.02182,"},{"key":"510_CR103","doi-asserted-by":"crossref","unstructured":"Wang H, Kaplan Z, Niu D, Li B (2020) Optimizing federated learning on non-iid data with reinforcement learning. In: IEEE INFOCOM 2020-IEEE conference on computer communications, pp 1698\u20131707 . IEEE","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"510_CR104","doi-asserted-by":"crossref","unstructured":"Xia Y, Ma B, Dou Q, Xia Y (2024) Enhancing federated learning performance fairness via collaboration graph-based reinforcement learning. In: International conference on medical image computing and computer-assisted intervention, pp 263\u2013272 . Springer","DOI":"10.1007\/978-3-031-72117-5_25"},{"key":"510_CR105","doi-asserted-by":"crossref","unstructured":"Xie Z, Liu M, Xue H, Au MH, Deng RH, Yiu S-M (2024) Direct range proofs for paillier cryptosystem and their applications. In: Proceedings of the 2024 on ACM SIGSAC conference on computer and communications security, pp 899\u2013913","DOI":"10.1145\/3658644.3690261"},{"key":"510_CR106","unstructured":"Xiong G, Wang S, Jiang D, Li J (2024) Personalized federated reinforcement learning with shared representations. In: Deployable RL: from research to practice@ reinforcement learning conference 2024"},{"key":"510_CR107","doi-asserted-by":"crossref","unstructured":"Xu Z, Zhang Y, Andrew G, Choquette-Choo CA, Kairouz P, McMahan HB, Rosenstock J, Zhang Y (2023) Federated learning of gboard language models with differential privacy. arXiv:2305.18465","DOI":"10.18653\/v1\/2023.acl-industry.60"},{"key":"510_CR108","doi-asserted-by":"crossref","unstructured":"Yang X, Huang W, Ye M (2024) Fedas: Bridging inconsistency in personalized federated learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11986\u201311995","DOI":"10.1109\/CVPR52733.2024.01139"},{"key":"510_CR109","unstructured":"Yin D, Chen Y, Kannan R, Bartlett P (2018) Byzantine-robust distributed learning: Towards optimal statistical rates. In: International conference on machine learning, pp 5650\u20135659. Pmlr"},{"key":"510_CR110","unstructured":"Yousefpour A, Shilov I, Sablayrolles A, Testuggine D, Prasad K, Malek M, Nguyen J, Ghosh S, Bharadwaj A, Zhao J et al (2021) Opacus: User-friendly differential privacy library in pytorch. arXiv:2109.12298"},{"key":"510_CR111","unstructured":"Zhang J-Q, Xu H-X, Ma Y-S, Ni L-N (2024) Fedqt: A federated learning model compression algorithm based on quicksort and top avg pruning"},{"key":"510_CR112","doi-asserted-by":"crossref","unstructured":"Zhou L, He Y, Zhai K, Liu X, Liu S, Ma X, Ye G, Chai H (2025) Fedcada: Adaptive client-side optimization\u00a0for accelerated and stable federated learning. In: ICASSP 2025-2025 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1\u20135. IEEE","DOI":"10.1109\/ICASSP49660.2025.10889407"},{"key":"510_CR113","unstructured":"Zhuansun Y, Li D, Huang X, Sun C (2024) Communication-efficient federated learning with adaptive compression under dynamic bandwidth. arXiv:2405.03248"},{"key":"510_CR114","unstructured":"Zuo S, Yan X, Fan R, Hu H, Shan H, Quek TQ (2024) Byzantine-resilient federated learning with adaptivity to data heterogeneity. arXiv:2403.13374"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00510-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00510-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00510-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:35:57Z","timestamp":1775208957000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00510-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":114,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["510"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00510-2","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"4 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"101"}}