Federated Learning for Internet of Things: A Comprehensive Survey
Open accessThe DOI matches its Crossref record; 232 of the 237 references it cites were found in a registry or an index, and 4 are not checked yet; 47 of the 198 sources its claims cite were checked for support.
Abstract
The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may not be feasible in realistic application scenarios due to the high scalability of modern IoT networks and growing data privacy concerns. Federated Learning (FL) has emerged as a distributed collaborative AI approach that can enable many intelligent IoT applications, by allowing for AI training at distributed IoT devices without the need for data sharing. In this article, we provide a comprehensive survey of the emerging applications of FL in IoT networks, beginning from an introduction to the recent advances in FL and IoT to a discussion of their integration. Particularly, we explore and analyze the potential of FL for enabling a wide range of IoT services, including IoT data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy and security. We then provide an extensive survey of the use of FL in various key IoT applications such as smart healthcare, smart transportation, Unmanned Aerial Vehicles (UAVs), smart cities, and smart industry. The important lessons learned from this review of the FL-IoT services and applications are also highlighted. We complete this survey by highlighting the current challenges and possible directions for future research in this booming area.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This survey argues that federated learning (FL) can make IoT systems more privacy-preserving, scalable, and communication-efficient by training models on distributed devices instead of centralizing raw data. It reviews FL in IoT services and applications, then summarizes lessons learned and open research challenges.
Key findings
- FL is presented as an alternative to raw-data sharing in IoT: it enables “privacy-enhanced and scalable data sharing” and keeps raw data local while sharing learning results.
- The survey identifies several IoT service areas where FL is useful: data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing, and IoT privacy/security.
- It also surveys FL in major application domains: smart healthcare, smart transportation, UAVs, smart city, and smart industry.
- In the paper’s taxonomy tables, several reported results include:
- IoT video data sharing with FL achieved 3.8% higher image-classification accuracy and 1.1% better object-detection performance over conventional FedAvg.
- A UAV-swarm FL scheme reduced the convergence round by 35% compared with non-joint schemes.
- A mobile crowdsensing FL scheme reported over 98% accuracy, with 23.9% runtime reduction and 33.3% communication-latency reduction for gradient aggregation.
Methods
- This is a narrative survey, not an experimental study: it synthesizes prior FL and IoT literature and organizes it by service type, application domain, and FL architecture.
- The paper’s structure includes an overview of FL and IoT, then sections on FL for IoT services and FL for IoT applications, followed by lessons learned and research challenges.
- It also uses taxonomy tables to summarize prior work, including FL type, ML type, FL clients, FL aggregator, key contributions, and limitations.
Limitations
- The paper itself states that existing work leaves several areas insufficiently covered, motivating this survey; it says prior surveys did not provide a comprehensive review of FL in IoT networks and applications.
- It states that many FL-IoT problems remain open, including threats/security, communication and convergence issues, resource management, and the feasibility of deploying AI on constrained IoT sensors.
- Evident from the text: this is a high-level survey with no new dataset, no controlled experiment, and no direct empirical validation of the reviewed methods by the authors themselves.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





![Fig. 6 The architecture of federated learning-based data sharing for IoV with blockchain [52].](https://figures.cochat.ai/paper-figures/2558776f41b74540a5589e277f2ecf12/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-6.png)



![Fig. 10 Federated learning for smart healthcare: A case study for COVID-19 image classification with blockchain [128].](https://figures.cochat.ai/paper-figures/cc15722ada484d9c8d1ca77ec766f832/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-10.png)
![Fig. 11 Federated learning for UAV-based ground air quality monitoring [147].](https://figures.cochat.ai/paper-figures/4f905cb13a204d8fb7509bdec6f7b641/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-11.png)
![Fig. 12 Federated learning for cooperative industry [161].](https://figures.cochat.ai/paper-figures/690f5ab552054933b49389363afcd6da/federated-learning-for-internet-of-things-a-comprehensive-survey-figure-12.png)
Verification
Claims the paper makes
40 Valid · 7 Not valid · 135 Not checked · 63 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Moreover, the cooperation of IoT devices under the guidance of the FL process is able to improve the overall training accuracy of the learning model.”
What the sources say
- Disputedcites [59] [59] J. Ren, H. Wang, T. Hou, S. Zheng, and C. Tang, 'Federated LearningBased Computation Offloading Optimization in Edge ComputingSupported Internet of Things,' IEEE Access , vol. 7, pp. 69 194-69 201, 2019. - sourceExperimental — accuracy not yet measured
The Training Performance Under Different Tasks Probabilities section says FL-based training loses a small amount of model accuracy compared with centralized DRL training, rather than improving it. The Algorithm 1 discussion reports that FL-based training approaches centralized DRL performance after several model aggregations, not that cooperation improves training accuracy. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Due to the contemporary features, DFL can be integrated with P2Pbased communication technologies such as blockchain [37] to build decentralized FL systems.”
What the sources say
- Partly supportedcites [37] [37] D. C. Nguyen, P. N. Pathirana, M. Ding, and A. Seneviratne, 'Integration of Blockchain and Cloud of Things: Architecture, Applications and Challenges,' IEEE Communications Surveys & Tutorials , pp. 1-1, 2020. - sourceExperimental — accuracy not yet measured
The “Peer-to-Peer Learning” section (page unavailable) describes fully decentralized federated learning in which clients communicate with neighboring clients without a central server. It does not identify blockchain as a communication technology for such a system or discuss integrating it with decentralized federated learning. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“To overcome these challenges, FL comes as a natural solution to perform attack detection algorithms for distributed IoT networks [82].”
- Also stated in: § A. Lessons Learned from FL-IoT Services · plain
“FL comes as a natural solution to perform attack detection algorithms for distributed IoT networks [82].”
What the sources say
- Supportedcites [82] [82] T. D. Nguyen, S. Marchal, M. Miettinen, H. Fereidooni, N. Asokan, and A.-R. Sadeghi, 'D ¨ IoT: A Federated Self-learning Anomaly Detection System for IoT,' in Proceedings of the International Conference on Distributed Computing Systems (ICDCS) , Dallas, TX, USA, Jul. 2019, pp. 756-767. - source
Section IV, “Federated Learning Approach,” says the system learns anomaly-detection models from traffic collected at gateways monitoring separate IoT networks and chooses federated learning because data are distributed and each client has little data. The paper thus supports using federated learning for attack detection in distributed IoT networks; “natural solution” is the citing authors’ characterization. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Also stated in: § A. Lessons Learned from FL-IoT Services · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Simulations from different offloading task probabilities indicate an improvement in the offloading performance in terms of high system utility and low task transmission latency.”
What the sources say
- Partly supportedcites [59] [59] J. Ren, H. Wang, T. Hou, S. Zheng, and C. Tang, 'Federated LearningBased Computation Offloading Optimization in Edge ComputingSupported Internet of Things,' IEEE Access , vol. 7, pp. 69 194-69 201, 2019. - sourceExperimental — accuracy not yet measured
In “Training Performance Under Different Tasks Probabilities” (page not provided), the simulations report higher average utility for FL than for centralized DRL. They do not show consistently lower task transmission time: it is similar at low task-generation probabilities and higher for FL at probabilities of 0.7–0.9. The claim overstates the transmission-latency result. (LLM, conf=0.89)
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In traditional IoT systems [39], [40], AI functions are often placed on data centers or cloud servers, which is obviously not scalable to the exponential growth of IoT devices and the high data distribution of large-scale IoT networks.”
What the sources say
- Partly supportedcites [39] [39] M. Mohammadi, A. Al-Fuqaha, S. Sorour, and M. Guizani, 'Deep Learning for IoT Big Data and Streaming Analytics: A Survey,' IEEE Communications Surveys & Tutorials , vol. 20, no. 4, pp. 2923-2960, 2018. - sourceExperimental — accuracy not yet measured
Section VI (page unavailable) says IoT analytics tasks are currently performed in the cloud and that moving some analytics closer to devices can avoid transmitting large amounts of data to distant cloud nodes. It does not say cloud-based AI is inherently unable to scale with IoT growth or distributed data; the Enabling Technologies and Platforms subsection instead calls scalable cloud-centric analytics for massive IoT data an important research area. (LLM, conf=0.86)
- Partly supportedcites [40] [40] D. C. Nguyen, P. Cheng, M. Ding, D. Lopez-Perez, P. N. Pathirana, J. Li, A. Seneviratne, Y. Li, and H. V. Poor, 'Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective,' IEEE Communications Surveys & Tutorials , pp. 1-1, Sep. 2020. - sourceExperimental — accuracy not yet measured
The Introduction (I. INTRODUCTION) supports the first half of the attribution: 'Traditional big data-based machine learning systems collect data to a certain location, such as the central servers,' and the same section states that current systems 'depend on the collection of vehicle data to the cloud, which is unable to satisfy the needs of emerging services,' with cloud collection 'requir[ing] a high bandwidth and incur[ring] a high delay.' However, no passage in our copy frames the limitation as a lack of scalability to the *exponential growth of IoT devices* or to *high data distribution in large-scale IoT networks*; the paper's stated drawbacks are bandwidth/delay, privacy (GDPR) and inadequacy for emerging vehicular services, and its scope is vehicular IoT rather than traditional IoT generally. So the centralised-placement description is supported while the scalability-to-device-growth rationale attributed here is not stated by this source. (LLM, conf=0.75)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
107 more claims · 22 with their cited sources checked
Create a free account to see all 245 claims and to verify the 58 references still open.
- Probably not a substantial claim. 56
- It may state two separate claims as one. 89
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This assures that sensitive data never leave the device or institution, preserving privacy and reducing the risks associated with data breaks [7].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [7]
Experimental — accuracy not yet measured
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Advances and Open Problems in Federated Learning
Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.04977 · Cited by 7,857
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015 · cited 3×
“1) FL for Smart Healthcare: FL can provide a number of efficient solutions for smart healthcare and potentially reshapes the current intelligent healthcare systems by proving AI functions for supporting healthcare services while improving user privacy and reducing low latency with the cooperation of multiple entities…”
BackgroundInfluentialFederated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766
The Future of Digital Health with Federated Learning
Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B., Maier-Hein, K., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.08119 · Cited by 3,495
Industry 4.0: A survey on technologies, applications and open research issues
Lu, Y. (2017) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2017.04.005 · Cited by 3,012 · cited 1×
“0 is the new concept whose aim is to promote the automation of manufacturing and industrial operations, which stimulates the development of smart factories for producing smart products without human involvement [168].”
BackgroundLin, J., Yu, W., Zhang, N., Yang, X., Zhang, H., & Zhao, W. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2683200 · Cited by 2,793
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565 · cited 4×
“Several possible selection factors for this selection can be channel conditions and the importance of local updates of each IoT device [17].”
BackgroundMethodInfluential
Research works printed but not linked: 5
- [4] 'Cisco Global Cloud Index: Forecast and Methodology, 2016-2021 White Paper,' 2020. [Online]. Available: https://www.cisco.com/c/en/ us/solutions/executive-perspectives/annual-internet-report/index.html -
- [105] S. Li, Y. Cheng, Y. Liu, W. Wang, and T. Chen, 'Abnormal Client Behavior Detection in Federated Learning,' arXiv:1910.09933 [cs, stat] , Dec. 2019, arXiv: 1910.09933. - · arXiv
- [206] H. Cai, C. Gan, L. Zhu, and S. Han, 'TinyTL: Reduce Memory, Not Parameters for Efficient on-device Learning,' Advances in Neural Information Processing Systems , vol. 33, 2020. -
- [209] F. Giust, X. Costa-Perez, and A. Reznik, 'Multi Access Edge Computing Overview of ETSI - IEEE Future Networks,' IEEE 5G Tech Focus , vol. 1, no. 4, p. 4, 2017. -
- [2] M. Mohammadi and A. Al-Fuqaha, 'Enabling Cognitive Smart Cities Using Big Data and Machine Learning: Approaches and Challenges,' IEEE Communications Magazine , vol. 56, no. 2, pp. 94-101, Feb. 2018. -
Cited by
Items 1,401–1,500 of 1,507
Collaborative Intelligence for Cloud–Edge–Terminal Architecture in Artificial Intelligence of Things
Mohan, D. S., Rani, P., Rajput, G. K., Kaur, K., Varshney, S., & Hussein, L. (2026) · Intelligent systems reference library · doi:10.1007/978-3-032-21753-0_14
Reis, M. J. C. S., Serôdio, C., & Branco, F. (2026) · Electronics · doi:10.3390/electronics15143069 · Cited by 1
Xiao, D., Zhang, Z., & Huang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3400-4_12
CE-FedAvg: A Communication-Efficient Federated Learning Framework for LoRaWAN-Based Edge AI
Razaghi, S., & Aral, A. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587288
“Nguyen et al. [14] survey FL techniques for IoT and emphasize communication efficiency and device heterogeneity as central challenges in low-power environments.”
Oh, J., Won, D., Truong, T. P., et al. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587505
“However, its performance is limited by a communication bottleneck, as repeated high-dimensional updates over scarce wireless bandwidth [5].”
Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias–Variance Trade-off
Abrar, M. F. U., & Michelusi, N. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587568 · Cited by 4
“…private datasets coordinate with a central parameter server (PS), e.g., an edge or cloud server, by transmitting only model parameters or gradients [2], [3] is typically solved by first-order optimization methods (e.g., mini-batch SGD): in each round, the PS broadcasts the current model w t ,…”
Deng, H., Yan, Y., & Tong, L. (2026) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops63917.2026.11586578
“This paradigm is particularly valuable in edge computing scenarios where data privacy is of paramount importance, including mobile keyboard prediction [3], healthcare analytics [4], and Internet of Things (IoT) applications [5].”
Federated Learning for Energy-Aware IoT Communication: Reducing Overhead While Preserving Privacy
nambiar, M., Rekha, V. S. D., Enitha, A., Nidhya, M. S., Prasad, B. V. V. S., & Tiwari, M. (2026) · International Conference on Emerging Research in Smart Electronics and Machine Informatics (ECMI) · doi:10.1109/ecmi68341.2026.11602980
“Although effective in terms of computational capability, such approaches suffer from excessive communication overhead, high energy consumption, and significant privacy risks, making them unsuitable for large - scale and resource - constrained IoT environments [8], [10].”
Gao, Y.-T., Chen, X., Deng, H., Xie, Y., & Chen, J. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3714152
“In this section, we explore the practical application of CVFL-Pro in the emerging field of smart transportation [25].”
Rawat, M., Rawat, M., & Singal, G. (2026) · Wireless Personal Communications · doi:10.1007/s11277-026-12181-3
“9 Issues with FL: data heterogeneity and adversarial attacks more sophisticated FL algorithms, such as those incorporating differential privacy [39 ] or secure multi-party computation and robust aggregation techniques (e.g., Byzantine-resilient aggregation) could further improve the privacy and…”
Wang, Z., Liu, Y., Teng, S., & Ju, L. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-22542-9_32
Blockchain and AI Convergence for Securing IoT Networks
Hassan, Y. M. I. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3857-6.ch003
Cybersecurity Awareness and Resilience Against Darknet Threats
Madke, T. P., Shaikh, A., & Das, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-9755-9.ch014
Alkhorasani, H., Zolait, A. H., & Alawag, A. M. (2026) · International Conference on Frontiers of Engineering and Emerging Technologies (FET) · doi:10.1109/fet68771.2026.11601477
“The previous background surveys further characterize the landscape, as Nguyen et al. [43] explored FL in the context of IoT in terms of communication efficiency, statistical heterogeneity, and adherence to GDPR, Zhang [10] outlined a general overview of FL applications such as banking and…”
Rosado, G. A. H. (2025) · CognitivaTech Ingeniería de Software Inteligente y Sistemas Adaptativos · doi:10.63688/cognitivatech.v2.i1.30
An Adaptive Resource-Aware Node Selection for Federated Learning in IoT Using Genetic Optimization
Slama, M., Elkosantini, S., Suh, W., & Lee, S. M. (2026) · Intelligence in Business and Industry (IBI) · doi:10.1109/ibi68858.2026.11604109
“Consequently, the effectiveness of FL in IoT environments is highly dependent on efficient resource-aware coordination mechanisms that jointly consider communication cost and QoS throughout the learning process [4].”
InfluentialKumaresan, S., Thirumal, L., Ellappan, V., & Selvam, R. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150600186
Lv, R., & Sun, S. (2026) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai70471.2026.11607714
“Under the combined effect of these two types of heterogeneity, the local model updates generated by different clients may diverge, leading to difficulties in global model aggregation and ultimately degrading the convergence speed and generalization performance of the model[3].”
PFedKAN: A New Paradigm for FedKAN Client Selection Based on Non‐iid
Jiang, Z., Du, Y.-T., Chen, X., et al. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/2675763
Zhang, J., An, Z., Wang, X., & Liu, J. (2026) · Comput. Networks · doi:10.1016/j.comnet.2026.112611
An Enhanced Adaptive Intelligent Clustering (AI-C) in Networks of Wireless Sensors
Zubairu, B., & Ibrahim, S. (2026) · WSEAS Transactions on Computers archive · doi:10.37394/23205.2026.25.10
HFL@AGriNET: Deployment of Hierarchical Federated Learning-based Agricultural NetworkPreprint
Gayen, A., Paul, S., Bhattacharya, A., Mondal, K., & Jana, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7192451
Mechanism Design for Federated Learning With Non-Monotonic Network Effects
Li, X., Luo, B., Huang, J., & Luo, Y. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3717853
“Mechanism Design for FL Social Welfare: The mechanism design for FL social welfare optimization has made considerable progress (e.g., [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32]), as summarized in recent surveys [3], [4], [5], [6], [7], [8].”
FSM: Privacy-Preserving Federated Learning for On-Device Child Screen Content Monitoring
Mehta, M., Kothari, H., Mathukia, N., et al. (2026) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit69683.2026.11621631
“Federated Learning (FL) [1] has matured significantly from early conceptual models to highly sensitive domains like healthcare [14] and the broader Internet of Things [16].”
Al-Sadi, D., & Tawalbeh, L. (2026) · International Conference on Artificial Intelligence Systems (AIS) · doi:10.1109/ais69919.2026.11621604
“IoT devices train local models on private data and share only gradient updates with a central aggregation server, so sensitive information never leaves the device [1], [5].”
InfluentialSynCal-Mix: Anchor-Calibrated Synthetic Rare-Event Support for Federated IoT Sensing
Shao, X., & Liu, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3717624
Choudhari, A., & Bhalekar, M. A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31216-7_7
ZTE-FL: Dual-layer trust aggregation for secure federated learning in IIoT
Tom, A. K., Whaiduzzaman, M., Alazab, A., & Jan, T. (2026) · Internet of Things · doi:10.1016/j.iot.2026.102045
Diop, F., & Niang, I. (2026) · International Conference on Federated Learning and Intelligent Computing Systems (FLICS) · doi:10.1109/flics70075.2026.11621948
Cost-Effective Processing of IoT Data in the Computing Continuum
Karagiannis, V., Ignjatović, D., Iosifidis, A., & Schulte, S. (2026) · IEEE International Conference on Fog and Edge Computing (ICFEC) · doi:10.1109/icfec69006.2026.00009
“Nguyen et al. [24] provide a comprehensive review of FL approaches for the IoT, and describe specific target applications, e.g., for privacy, security, and crowd-sensing.”
A Distributed Difference-Aware Alignment Framework for Robust Federated Graph Learning
Wang, X., Cheng, J., Wang, L., et al. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3718246
Adaptive Intelligence for UAV Network Security With Architectures, Mechanisms, and Open Challenges
Kumar, S., Khushbu, J., & Rathore, N. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0413-5.ch010
Chander, N., Kumar, G. A., Kumar, P. S., Kiran, I. S., Goud, B. S., & Prathap, D. S. (2026) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc69250.2026.11625022
“D. C. Nguyen et al. [17] investigated the concept of federated learning to implement privacy-preserving methods to the IoT infrastructure, and discussed issues of data sharing, scalability, and decentralized model training.”
Balakrishnan, M., Madhusudhanan, S., & Jose, A. C. (2026) · Security and Privacy · doi:10.1002/spy2.70240
Security, Privacy, and Trust Challenges in TinyML-Based IoT Edge Intelligence
Obi-Akwari, O. E., Igbokwe, M. M., Charles, I. E., Adedokun, M. T., Olawoyin, O. O., Olokun, M. S., & Nwanakwaugwu, A. C. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0615-3.ch010
Sun, R., Yumin, Z., Ojha, V., Shah, T., Wei, B. W., & Ranjan, R. K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7212327
Zhao, Z., Luan, Y., Song, J., Li, L., & Peng, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3719117 · Cited by 1
“By exchanging model updates instead of raw samples, FL alleviates the data-silo issue and supports privacy-preserving analytics across distributed sensing and edge computing infrastructures [4].”
Latif, S., Javed, H., & Shaheen, S. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1909
AI-Driven Predictive Maintenance Combining Edge IoT and Federated Learning for SMEs
Anumula, S. K., Rai, D. K., Kunthu, B. R., & Taware, R. N. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-28307-8_15
A.Mallika, Christy, A. A., Krishnamoorthy, P., Priya, A., Ebenezer, D. D., & Shroff, A. D. (2026) · International Conference on Inventive Computation and Information Technologies (ICICIT) · doi:10.1109/icicit69063.2026.11634178
Federated Learning–Based Intrusion Detection For Privacy-Preserving Iot Security
Hemlathadhevi, A., Shabin.P, A., Balaji., M., Boni Das, B., & Azhaguraj, A. (2026) · International Conference on Data Science for Cyber-Physical Systems Resilience using Advanced Applications (ICDCA) · doi:10.1109/icdca69396.2026.11620459
“By allowing models to be trained locally on IoT devices and sharing only mathematical model updates rather than raw data, Federated Learning (FL) emerged as a crucial paradigm change to solve these restrictions [2], [11].”
Stress Monitoring with Machine Learning: Detecting and Managing Mental Health
Jiang, S., Li, Y., Firouzi, F., Chakrabarty, K., & Elbogen, E. B. (2025) · Springer eBooks · doi:10.1007/978-3-032-09253-3_4
Privacy-Preserving Federated Learning for Anomaly Detection: A Comprehensive Framework
Kong, L., Lu, Y., & Wang, W. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-1884-4_11
Lakinana, B., & Chilukuri, K. C. (2026) · International Journal of Emerging Research in Engineering Science and Management · doi:10.58482/ijeresm.v5i3.5
A Verifiable Accountable Anonymous Authentication Interface for Cross-Silo Federated Learning
Wang, Z. (2026) · IEEE Access · doi:10.1109/access.2026.3721480
“A3FL targets regulated cross-silo FL among authenticated institutions, a deployment pattern discussed in FL security and IoT-oriented FL surveys [2], [40], [41].”
A Comprehensive Review of Privacy-Preserving Techniques in Federated Learning for IoT Networks
Lawson, J., & Wilson, D. (2026) · Journal of Global IT Dynamics · doi:10.67808/jgidv1i1-001-260807110403
Sarika, & Dass, R. (2026) · Optoelectronics Instrumentation and Data Processing · doi:10.3103/s8756699026700421
A Comprehensive Survey on Embedded Deep Learning Algorithms for Smart IoT Monitoring Systems
Alalwany, W. S. H., & Fahim, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25568-6_9
Rajasekar, M., Thamizhsudar, M., Manikandan, M., et al. (2026) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon69332.2026.11629820
Six major risks in modern society: Research progress and future directions
Zhang, Q., Hu, Y., & Wang, S. (2026) · Risk sciences. · doi:10.1016/j.risk.2026.100060
Mastoi, Q.-U.-A., Phung, K., & Morley, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35390-0_11 · Cited by 1
Sun, T., Lu, Q., Zhang, H., et al. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3723076
“Federated device identification mitigates many of these concerns by keeping raw data local and exchanging only model updates, thereby improving data confidentiality and avoiding continual raw-data transfer [9].”
Blockchain-Enabled Federated Learning for Collaborative Autonomous Vehicles
Duguleană, M., & Voinea, G.-D. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32726-0_10
Heterogeneous edge AI orchestration: A systematic review, taxonomy and future directions
Ali, B., Gill, S. S., Cuadrado, F., & Uhlig, S. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101044 · Cited by 1
Federated Learning-based Secure Mobile Edge Computing for Intelligent Android Applications
Musunuru, B. C. (2026) · International Conference on Intelligent and Sustainable AI Systems (ICOSAAS) · doi:10.1109/icosaas68663.2026.11649270
“However, issues such as communication overhead, non-independent data distribution, and client heterogeneity remain significant research challenges [11].”
FedSE-1DSqueezeNet: a lightweight federated intrusion detection system for Internet of Things
Zhou, Q., Mao, X., & Chen, Y. (2026) · Cluster Computing · doi:10.1007/s10586-026-06482-2 · Cited by 1
“Accordingly, the design of efficient Intru - sion Detection Systems (IDS) capable of real-time detection”
Abdelhameed, O., Turnbull, B., & Koroniotis, N. (2026) · Cyber Security and Applications · doi:10.1016/j.csa.2026.100133 · Cited by 1
Walehiane, S., & Mohamed, E. (2026) · International Conference on Cybersecurity, Digital Forensics, and AI Applications (ICCSDFAI) · doi:10.1109/iccsdfai70505.2026.11647961
“In cybersecurity, FL has been applied to intrusion detection [4], [5]malware classification [9], [10], and IoT anomaly detection [11], [12], [13].”
LBSFL: a lightweight robust federated learning method for IoT
Ma, W., Tian, W., Zhao, Q., & Wang, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01110-w
“This paradigm effectively prevents the leakage of raw data and mitigates data silo issues (Zhang et al. 2021) as well as privacy risks at the technical level (Nguyen et al. 2021).”
Eziama, E. U., Okafor, K. C., Diovu, R. C., Agajo, J., & Onwujekwe, G. (2026) · E3S Web of Conferences · doi:10.1051/e3sconf/202673502007
A Lightweight Federated Learning Intrusion Detection Framework for the Internet of Things
Xu, S. (2026) · International Conference on Information Communication, IoT Technology, and Smart Cities (IITS) · doi:10.1109/iits69561.2026.11648442
“To validate the effectiveness and efficiency of the proposed LF-IDS framework, we conduct extensive experiments on two widely adopted benchmark datasets: NSL-KDD [3] and N-BaIoT [3].”
Islam, M. Z., Afzel Noore, B., Adarbah, H. Y., Sagar, A. S. M. S., & Haider, A. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3723733
“The split-embedding strategy prevents gradient-inversion attacks and reduces communication overhead relative to FL approaches by transmitting compact intermediate embeddings rather than repeated model updates [17].”
InfluentialA review of federated learning: architectures, challenges, and targeted solutions
Velaei, M., Ghahramani, H., Ghaffari, A., & Derakhshanfard, N. (2026) · Cluster Computing · doi:10.1007/s10586-026-06286-4 · Cited by 1
“At the end of the training pro - cess, each node obtains the same global model along with its personalized model [ 2 ].”
InfluentialMa, G., Yu, D., Zhang, E., & Sun, H. (2026) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai70753.2026.11655101
“As the technology expands, FL has shown strong potential in the Internet of Things (IoT) [4] and has been systematically discussed in broader FL surveys [5], [6], [60], [61].”
Kalapaaking, A. P., Stephanie, V., Samikwa, E., Khalil, I., & Braun, T. I. (2026) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge72783.2026.00026
“Devices involved in the FL process may have diverse computing and communication capabilities [9].”
IoTScal-2CoM-ALO: An Adaptive Load Orchestration Framework for Scalable Collaborative IoT Systems
Abourriche, S., Zyane, A., & Ghammaz, A. (2026) · International Conference on Future Internet of Things and Cloud (FiCloud) · doi:10.1109/ficloud70576.2026.00055
“System resilience has been enhanced by strategies like federated architectures and multi-tier models [14], and distributed CSE deployments within oneM2M have assisted in lowering single points of failure [15].”
Optimizing Federated Learning for Botnet Defense: A Comparative Study of Aggregation Strategies
Yamani, Y. E., Baddi, Y., & Kamoun, N. E. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-21200-9_29
Cunha, W. L., Gonzalez, L. F. G., Guidoni, D. L., et al. (2026) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot69657.2026.00174
Bandwidth-Aware Decentralized Federated Learning in Wired Networks
Tajiri, K., & Kawahara, R. (2026) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn69946.2026.11662732
“As a solution to these problems, federated learning (FL) has gained attention [1]–[3].”
Wang, W., Dai, J., Yang, Z., Zhang, Z., Yang, Q., Si, X., Sun, Y., & Yang, K. (2026) · IET Communications · doi:10.1049/cmu2.70213
Insourcing IoT Security with Edge Agents
Zhang, Y., Hong, S. M., & Gu, G. (2026) · Proceedings/Proceedings - International Conference on Computer Communications and Networks · doi:10.1109/icccn69946.2026.11662543
“Recent federated learning approaches train models across distributed IoT devices without centralizing data [38], but focus on model training rather than real-time security service delivery.”
Liang, Y., Li, C., Wu, Y., Qiu, J., Yan, Y., & Chen, Z. (2026) · doi:10.1145/3821820.3821823
“In decentralized IoT environments where data is collected from numerous edge sensors, the training pipeline is highly susceptible to such injections [5].”
Digital Twin and Virtual Monitoring of a 6-DOF Robotic Manipulator
Rigó, L., Fabianová, J., & Kovalčík, J. (2026) · Logistics · doi:10.3390/logistics10090205
Clinical risk-aware reinforcement learning for latency-constrained healthcare IoT scheduling
Jumah, J. A. B., Mirghani, H. O., Alateeq, S., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-68894-9
“…learning approaches have been investigated to preserve privacy while enabling collaborative intelligence across distributed IoT healthcare devices 2 , whereas security analyses of MEC-enabled 5G applications have highlighted vulnerabilities that must be considered in practical deployments 3 .”
LIA-FL: A containerised federated learning platform for AIoT time-series forecasting
Fas, À. R., Goterris, J., Díaz-Rivero, A., Martínez, C. S., & Trilles, S. (2026) · SoftwareX · doi:10.1016/j.softx.2026.103000
A Privacy-Preserving Intrusion Detection System for IoT Networks Using Federated Learning
Alraheem, A. A., Obeid, A., & Shaker, B. N. (2026) · Wasit Journal of Engineering Sciences · doi:10.31185/wjes.vol14.iss3.997
“FL guarantees the security of data privacy, minimizes latency, decreases power usage, and facilitates training directly on devices [27].”
KIPONGO, J., Swart, T. G., & Esenogho, E. (2026) · Soft Computing · doi:10.1007/s00500-026-11432-6 · Cited by 1
A Cross-Layer Review of Intelligent, Secure, and Privacy-Preserving Internet of Vehicles
Alayedi, M., & Jaradat, A. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8090277
Khan, M. A., Alkhattabi, M., Shah, S. F. A., Khan, M. A., Mazhar, T., Saudagar, A. K. J., Rehman, A. U., Hamam, H., & Cui, J. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2025.00.347
Mellamarthi, M., Summaq, A., Kumar, M. P., & Chinnadurai, S. (2026) · IEEE Access · doi:10.1109/access.2026.3732519
“…upstream bandwidth cost scales poorly with device count, latency introduced by round-trip transmission conflicts with time-sensitive applications, and data protection legislation in many jurisdictions prohibits transferring personal records to third-party servers without explicit consent [3], [4].”
Liang, T., Wang, X., Yu, M., Yuan, S., & Guan, Z. (2026) · Digital Communications and Networks · doi:10.1016/j.dcan.2026.09.007
Police UAV Operator Competency Assessment and Training Optimization Based on Cloud-IoT Collaboration
Hou, H. (2026) · International Journal of Digital Crime and Forensics · doi:10.4018/ijdcf.422092
Similarity-Promoting Resilient Adaptive Aggregation in Peer-to-Peer Machine Learning
Bhowmick, C., & Koutsoukos, X. (2026) · Machine Learning · doi:10.1007/s10994-026-07162-3
“…the vast computational resources and diverse datasets spread across multiple nodes, as found in sec - tors such as Internet-of-Things (IoT) systems (Nguyen et al., 2021 ), sensor networks (Seng et al., 2022 ), smart city (Jiang et al., 2020 ), autonomous vehicles (Nguyen et al., 2022; Zhang et…”
A Comprehensive Review of Federated Learning for Green 6G-IIoT Ecosystems
Tiwari, S., Prakash, S., Tiwari, V. K., & Kumar, D. (2026) · International Conference on Green Technologies and Sustainable Solutions (GTSS) · doi:10.1109/gtss68743.2026.11679691
“This illustrates how the IoT data is exploding at the network edges [9].”
Machine Learning-Based Crime Prediction for Smart Policing: A Replicable Application
Aguilar-Ortíz, J., Díaz-Parra, O., Ruíz-Vanoye, J. A., Vera-Jiménez, M. A., Zamudio-García, V. M., Trejo-Macotela, F. R., Domínguez-Mayorga, C. R., & Ramos, M. Y. G. (2026) · Advances in wireless technologies and telecommunication book series · doi:10.4018/979-8-2600-1533-9.ch015
Le, H., Okada, S., & Huynh, V. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135161
Alam, M. A., Mimi, A., Islam, M. M., Sharmin, K., & Bhuiyan, M. R. I. (2026) · SAGE Open · doi:10.1177/21582440261489866
Prabha., A., Pallavi, I. S., Pavani, P. R., et al. (2026) · doi:10.1109/iccvbic71195.2026.11689381
“Recent works have used FL to IoT and WSN scenarios in activities like intrusion detection, traffic prediction, and optimizing energy [9].”
Ajdani, M., & Asmani, M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06562-3
“Federated learning-based IDS [ 15–17] address privacy and distributed training.”
Driving Sustainable Smart Buildings through Federated Intelligence and Digital Twin Integration
Rajaram, P., & Swathika, O. V. G. (2026) · IEEE International Conference on Artificial Intelligence Implementation & Applications (ICAIIA) · doi:10.1109/icaiia70172.2026.11691649
“The initial studies show the significance of digital twins in cyber-physical systems and industries [13], [14].”
From Flight to Intelligence: UAV Applications and Federated Learning Approaches
Aldehim, G., Alkhattabi, M., Shah, S. F. A., et al. (2026) · IET Intelligent Transport Systems · doi:10.1049/itr2.70332
A systematic review of federated learning applications in mitigating insider threats
Mdaghri, A. A., Alae, A., & Hilali, A. A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116478
Leveraging federated learning for smart grids: A comprehensive survey
Husnoo, M. A., Anwar, A., & Rahman, M. A. (2026) · Cyber-Physical Energy Systems · doi:10.1016/j.cpes.2026.07.002 · Cited by 1
Robust and Scalable Federated AC WLS State Estimation via Decentralised Consensus
Anwar, A. (2026) · IEEE Power & Energy Society General Meeting (PESGM) · doi:10.1109/pesgm58988.2026.11693757
“Although communication-efficient, server-based FL architectures introduce coordination bottlenecks and single points of failure [10].”
Chen, W., Ouyang, Z., Fu, Y., Zhong, R. Y., Yi, Z., & Cai, Y. (2026) · Computers & Industrial Engineering · doi:10.1016/j.cie.2026.112382
HyFair-FL: Fair and Accurate Federated Spectrum Sensing in Cognitive Radio Networks
Sharma, V., & Swain, P. (2026) · Wireless Personal Communications · doi:10.1007/s11277-026-12230-x
Piperigkos, N., Γκίλλας, Α., Anagnostopoulos, C., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3737417
“Due to these parameter efficient deep architectures, vehicles of the swarm can also collaborate and distributed train their models via federated learning (FL) [16] to assist and enhance the process of uncertainty estimation, as part of the overall CL task.”
Self-citation6G network security via federated AI and trust-aware access control for privacy preservation
Khediri, S. E. (2026) · Computer Communications · doi:10.1016/j.comcom.2026.108683
Khan, M. A. A., Luo, S., Mirani, I. K., Hamza, M., Rehman, Z. U., & Khan, S. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112833
FedVRU: Variational representation decomposition with uncertainty-aware refinement
Zhang, P., Bao, A., Lu, M., Xu, K., Li, M., & Guo, K. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134585
Metadata
- Authors
- Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H.
- Affiliations
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Data61 (AU)
- Deakin University (AU)
- UNSW Sydney (AU)
- Nanjing University of Science and Technology (CN)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2021
- Volume
- 23
- Issue
- 3
- Pages
- 1622-1658
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W3155912831
- Cited by
- 1,503
- References
- 171
- Citations by year
- 2026: 325 · 2025: 458 · 2024: 359 · 2023: 243 · 2022: 106 · 2021: 16
- FWCI
- 96.12
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- CSIRO Data61, Australia
- U.S. National Science Foundation (CCF-1908308)
- National Natural Science Foundation of China (61872184)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Science Applications › Mobile Crowdsensing and Crowdsourcing
- Keywords
- federated learning, Internet of Things, distributed learning, data privacy, data offloading, caching, attack detection, localization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.