Handling Privacy-Sensitive Medical Data With Federated Learning: Challenges and Future Directions.

Federated Learning (FL) is considered the key, enabling approach for privacy-preserving, distributed machine learning (ML) systems. FL requires the periodic transmission of ML models from users to the server. Therefore, communication via resource-constrained networks is currently a fundamental bottleneck in FL, which is restricting the ML model complexity and user participation. One of the notable trends to reduce the communication cost of FL systems is gradient compression, in which techniques in the form of sparsification are utilized. However, these methods utilize a single compression rate for all users and do not consider communication heterogeneity in a real-world FL system. Therefore, these methods are bottlenecked by the worst communication capacity across users. Further, sparsification methods are non-adaptive and do not utilize the redundant, similar information across users' ML models for compression. In this paper, we introduce a novel Dynamic Sparsification for Federated Learning (DSFL) approach that enables users to compress their local models based on their communication capacity at each iteration by using two novel sparsification methods: layer-wise similarity sparsification (LSS) and extended top- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> sparsification. LSS enables DSFL to utilize the global redundant information in users' models by using the Centralized Kernel Alignment (CKA) similarity for sparsification. The extended top- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> model sparsification method empowers DSFL to accommodate the heterogeneous communication capacity of user devices by allowing different values of sparsification rate <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> for each user at each iteration. Our extensive experimental results <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> All code and experiments are publicly available at: https://github.com/mahdibeit/DSFL. on three datasets show that DSFL has a faster convergence rate than fixed sparsification, and as the communication heterogeneity increases, this gap increases. Further, our thorough experimental investigations uncover the similarities of user models across the FL system.

Federated learning (FL)-a distributed machine learning that offers collaborative training of global models across multiple clients. FL has been considered for the design and development of many FL systems in various domains. Hence, we present a comprehensive survey and analysis of existing FL systems, drawing insights from more than 250 articles published in 2019-2024. Our review elucidates the functioning of FL systems, particularly in comparison with alternative distributed learning approaches. Considering the healthcare domain as an example, we define the building blocks of a typical FL healthcare system, including system architecture, federation scale, data partitioning, open-source frameworks, ML models, and aggregation algorithms. Furthermore, we identify and discuss key challenges associated with the design and implementation of FL systems within the healthcare sector while outlining the directions of future research. In general, through systematic categorization and analysis of existing FL systems, we offer insights to design efficient, accurate, and privacy-preserving healthcare applications using cutting-edge FL techniques.

Federated learning (FL) is a machine learning framework where multiple distributed edge internet-of-things (IoT) devices collaboratively train a model under the orchestration of a central server while keeping the training data distributed on the IoT devices. FL can mitigate the privacy risks and costs from data collection in traditional centralized machine learning. However, the deployment of standard FL is hindered by the expense of the communication of the gradients from the devices to the server. Hence, many gradient compression methods have been proposed to reduce the communication cost. However, the existing methods ignore the structural correlations of the gradients, and therefore lead to a large compression loss which will decelerate the training convergence. Moreover, many of the existing compression schemes do not enable over-the-air aggregation, and hence require huge communication resources. In this work, we propose a gradient compression scheme, named FedOComp, which leverages the correlations of the stochastic gradients in FL systems for efficient compression of the high-dimension gradients with over-the-air aggregation. The proposed design can achieve a smaller deceleration of the training convergence compared to other gradient compression methods since the compression kernel exploits the structural correlations of the gradients. It also directly enables over-the-air aggregation to save communication resources. The derived convergence analysis and simulation results further illustrate that under the same power cost, the proposed scheme has a much faster convergence rate and higher test accuracy compared to existing baselines.

Privacy and data security have become the new hot topic for regulators in recent years. As a result, Federated Learning (FL) (also called collaborative learning) has emerged as a new training paradigm that allows multiple, geographically distributed nodes to learn a Deep Learning (DL) model together without sharing their data. Blockchain is becoming a new trend as data protection and privacy are concerns in many sectors. Technology is leading the world and transforming into a global village where everything is accessible and transparent. We have presented a blockchain enabled security model using FL that can generate an enhanced DL model without sharing data and improve privacy through higher security and access rights to data. However, existing FL approaches also have unique security vulnerabilities that malicious actors can exploit and compromise the trained model. The FL method is compared to the other known approaches. Users are more likely to choose the latter option, i.e., providing local but private data to the server and using ML apps, performing ML operations on the devices without benefiting from other users’ data, and preventing direct access to raw data and local training of ML models. FL protects data privacy and reduces data transfer overhead by storing raw data on devices and combining locally computed model updates. We have investigated the feasibility of data and model poisoning attacks under a blockchain-enabled FL system built alongside the Ethereum network and the traditional FL system (without blockchain). This work fills a knowledge gap by proposing a transparent incentive mechanism that can encourage good behavior among participating decentralized nodes and avoid common problems and provides knowledge for the FL security literature by investigating current FL systems.

Internet of Things (IoT) systems are rightly receiving considerable interest for many real-world applications, from in-body networks to satellite networks. Such a massive-scale system generates a considerable amount of traffic data, making IoT systems a distributed data source generator. For many reasons, such as the functionality of IoT applications and Quality of Service (QoS) provisioning, classifying these traffic data is of high importance. In the last few years, widespread interest has been expressed in applying Machine Learning (ML)-based techniques for Network Traffic Classification (NTC) tasks. However, the traditional centralized learning-based traffic classifiers pose serious challenges, especially in IoT networks. The centralized ML techniques call for collecting a large amount of data from various IoT devices, which in turn introduces data governance and privacy challenges. Furthermore, in the centralized ML, training data need to be transferred to the Cloud, which increases communication cost and latency. To address these problems, we propose Federated Learning (FL) Internet of Things (IoT) Traffic Classifier (FLITC)-a Federated Learning (FL)-based IoT traffic classification method which is based on the Multi-Layer Perception (MLP) neural network and holds the local data unimpaired on IoT devices by sending only the learned parameters to the aggregation server. Our experimental results show that the FLITC beats centralized learning in preserving the privacy of sensitive data and offers a better degree of accuracy at the cost of a longer training time.

Federated Learning (FL) is a paradigm in distributed machine learning, which has gained significant attention in the recent years especially in the domain of Internet of Things. Federated Learning saves communication bandwidth when compared to centralized machine learning process and is also considered to be privacy preserving as the raw data at the clients need not be transmitted to the server for the FL learning. Recent studies on FL have exposed privacy vulnerabilities particularly in the form of Gradient Leakage Attacks (GLA) in which the adversaries can generate training data of the client from shared gradients or model updates from clients. The available solutions in the literature for GLA based on perturbing the gradients from clients leads to a drop in the performance of the FL system while attempting to preserve privacy. We propose HAFedL, an improved novel hessian aware adaptive privacy preserving FL scheme in which the performance of the model is not significantly affected due to the aspects introduced in the FL architecture to improve the privacy of the model against the GLA. The HAFedL is also robust to the data heterogeneity and device heterogeneity (particularly straggler effect) which may be present in the clients participating in the FL. The performance of HAFedL is tested for two applications- IoT device identification and digit classification. The proposed HAFedL scheme can be utilized in privacy sensitive domains such as smart city applications, Industrial Internet of Things, Internet of Robotic Things, Internet of Medical Things, etc.

The rapid expansion of wearable Internet of Things (IoT) devices in healthcare enables continuous monitoring of physiological signals but introduces critical privacy challenges, especially when training machine learning (ML) models on sensitive, distributed data. Federated learning (FL) addresses this by allowing collaborative model training without sharing raw patient data. However, most existing FL systems either transmit model updates in plaintext exposing them to inference attacks or adopt encryption schemes that are computationally prohibitive for resource-constrained devices. In this paper, we present a modular, privacy-preserving FL framework for health IoT that integrates Cheon-Kim-Kim-Song (CKKS) based Homomorphic Encryption (HE) at trusted edge nodes (e.g., home routers). This design offloads encryption from wearable devices, enabling secure model aggregation and update distribution while maintaining low energy and latency overheads. We evaluate our system on real-world datasets, measuring model utility (accuracy, F1), encryption latency, and end-to-end delay. Results demonstrate that our scheme preserves privacy with minimal performance degradation, supporting practical and secure deployment in realtime health monitoring scenarios.

Federated learning (FL) has been used to several domains, such as smart cities, intelligent healthcare systems, and sectors reliant on the internet of things (IoT). This is in response to the growing concern about privacy and security in machine learning applications. Clients may work together to train a global model using FL, even when they don't have access to the same data as before. Nevertheless, adversarial attacks may exploit the weaknesses of existing FL methods. Because of its design, protecting against harmful model changes and identifying them are both made difficult. Not enough has been investigated in the most current research on protecting the model's privacy while detecting FL from harmful updates. This study presented a solution to the problem of poisoning assaults on healthcare systems: federated learning based on blockchain technology with SMPC model verification. We start by removing the compromised model after verifying it via an encrypted inference procedure using the FL participants' machine learning models. After each participant's local model is checked, it is safely forwarded to the blockchain node for aggregation. In order to test our proposed framework, we used a variety of medical datasets in a number of studies.

Federated Learning (FL) is a Machine Learning (ML) paradigm in which multiple devices collaboratively train a model without sharing their local data. This decentralized approach provides significant privacy benefits, enabling compliance with data protection regulations and safeguarding sensitive user information by keeping raw data on local devices. Instead of transmitting raw data, FL sends model updates to a central aggregator to improve the global model. However, this process can result in higher Carbon Dioxide (CO₂) emissions compared to traditional centralized ML systems, due to the increased number of participating devices and communication rounds. This study evaluates the performance, convergence speed, energy efficiency, and environmental impact of FL models compared to centralized models, using the Modified National Institute of Standards and Technology dataset (MNIST) and Canadian Institute for Advanced Research-10 classes dataset (CIFAR-10). Four models were tested: two FL models and two centralized models. The evaluation focused on accuracy, number of training rounds to convergence, and total CO₂ emissions. To optimize both convergence and energy efficiency, a dynamic hill-climbing-based early stopping technique was introduced. After every 100 rounds, model accuracy improvements were assessed, and training was terminated early if further gains fell below a shrinking threshold, effectively reducing unnecessary computation and energy consumption. Results show that, under the tested conditions, FL models achieved competitive or higher accuracy than centralized models, particularly on non-Independent and Identically Distributed (IID) data distributions. For example, the federated MNIST model reached 98.79% accuracy with a significantly lower carbon footprint when early stopping was applied. Overall, the proposed optimization approach reduced CO₂ emissions by approximately 60% without substantial loss in accuracy. By integrating privacy preservation, explicit regulatory relevance, and a practical dynamic optimization method, this research demonstrates that FL can deliver strong model performance while meeting modern requirements for data privacy and environmental sustainability

Federated learning (FL) is a distributed model training paradigm that preserves clients’ data privacy. It has gained tremendous attention from both academia and industry. FL hyper-parameters (e.g., the number of selected clients and the number of training passes) significantly affect the training overhead in terms of computation time, transmission time, computation load, and transmission load. However, the current practice of manually selecting FL hyper-parameters imposes a heavy burden on FL practitioners because applications have different training preferences. In this paper, we propose, an automatic FL hyper-parameter tuning algorithm tailored to applications’ diverse system requirements in FL training. iteratively adjusts FL hyper-parameters during FL training and can be easily integrated into existing FL systems. Through extensive evaluations of for diverse applications and FL aggregation algorithms, we show that is lightweight and effective, achieving 8.48%-26.75% system overhead reduction compared to using fixed FL hyper-parameters. This paper assists FL practitioners in designing high-performance FL training solutions. The source code of is available at.

Federated learning is a collaborative/distributed machine learning system which is designed to address the privacy issues in centralized machine learning systems. The transparency and provenance of a machine learning model are important aspects of federated learning systems since they impact peoples&#x2019; lives in various domains (e.g., from healthcare to personal finance to employment). However, most of the existing federated learning systems deal with centralized coordinators which are vulnerable to attacks and privacy breaches. Also, they do not provide any standard transparency and provenance mechanisms for the resulting models. In this paper, we propose a blockchain and Model Card-based integrated federated learning system "Bassa-ML" providing enhanced transparency and trust for the models. Model parameter sharing, local model generation, model averaging, and model sharing functions are implemented using smart contracts. The generated models, model training information, and model reports are stored in the blockchain ledger as Model Card Objects. This results in enhanced transparency and auditability to the federated learning process.

Federated Learning (FL) is a collaborative machine learning (ML) framework that combines on-device training and server-based aggregation to train a common ML model among distributed agents. In this work, we propose an asynchronous FL design with periodic aggregation to tackle the straggler issue in FL systems. Considering limited wireless communication resources, we investigate the effect of different scheduling policies and aggregation designs on the convergence performance. Driven by the importance of reducing the bias and variance of the aggregated model updates, we propose a scheduling policy that jointly considers the channel quality and training data representation of user devices. The effectiveness of our channel-aware data-importance-based scheduling policy, compared with state-of-the-art methods proposed for synchronous FL, is validated through simulations. Moreover, we show that an ``age-aware'' aggregation weighting design can significantly improve the learning performance in an asynchronous FL setting.

• Trustworthy AI is a prerequisite for deploying FL in high-risk, multi-stakeholder domains. • Privacy-preserving guarantees alone are insufficient to sustain trust in agentic and dynamic FL systems. • We present a requirement-driven taxonomy of challenges aligned with Trustworthy AI principles, explicitly extended to agentic AI and LLM-enabled settings. • We present a coordination blueprint maps Trustworthy AI requirements to FL-native controls and decision-centric, auditable evidence across the lifecycle. • We reframe trust in FL as a continuously maintained operating condition and introduce coordination tools to operationalize it. • We propose Trust Report 2.0 to operationalize trust as evidence, not assumptions, by surfacing what decisions were made, why, and under which constraints, without centralizing raw data. Federated Learning (FL) enables privacy-preserving collaborative learning, yet deployments increasingly show that privacy guarantees alone do not sustain trust in high-risk settings. As FL systems move toward agentic AI, large language model–enabled, and dynamically adaptive architectures, trustworthiness becomes a system-level problem shaped by autonomous decision-making, non-stationary environments, and multi-stakeholder governance. We argue for Trustworthy FL (TFL), treating trust as a continuously maintained operating condition rather than a static model property. Through the lens of Trust Report 2.0, we propose a requirement-driven taxonomy of challenges grounded in TAI and explicitly extended to account for control-plane decisions, agency, and system dynamics across the federated lifecycle. Building on this diagnosis, we introduce a coordination blueprint that structures cross-requirement trade-offs, decision justification, and governance alignment in TFL systems. To operationalize assurance, Trust Report 2.0 is instantiated as a lightweight, privacy-preserving artifact that surfaces decision-centric trust evidence without centralizing raw data. We illustrate applicability via healthcare as a stress-test domain, focusing on oncology FL under regulatory pressure and clinical risk.

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed; and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×.

This article provides a comprehensive survey of aggregation strategies in federated learning (FL). This decentralized machine learning (ML) paradigm enables multiple clients to collaboratively train models without sharing their local datasets. Aggregation is a pivotal aspect of FL, as it integrates model updates from diverse clients into a unified global model while addressing critical challenges such as data heterogeneity, scalability, and privacy preservation. The study categorizes aggregation strategies into three primary approaches: data-centric, model-centric, and secure aggregation, each tailored to address distinct problems in FL systems. Data-centric strategies focus on addressing non-independent and identically distributed (non-IID) data across clients, ensuring that model updates account for imbalances in data distributions. Model-centric strategies optimize the aggregation of model parameters, emphasizing techniques such as weighted averaging and model distillation to improve model performance across clients with diverse data characteristics. Secure aggregation techniques aim to enhance privacy and robustness, protecting client data from potential adversarial threats through encryption-based methods like secure multi-party computation (SMPC) and Byzantine-resilient techniques. The analysis delves into the advantages and limitations of these aggregation strategies, particularly their role in tackling challenges like non-IID data, communication efficiency, and resistance to adversarial attacks. Furthermore, the article identifies existing research gaps in FL, including the need for more scalable and robust aggregation methods capable of reducing communication costs, enhancing privacy guarantees, and improving performance in highly heterogeneous environments. These insights provide a roadmap for future research aimed at advancing aggregation strategies in FL to improve model accuracy, security, and efficiency in real-world applications.