Fair and Robust Federated Learning via Decentralized and Adaptive Aggregation based on Blockchain

Trustiness-based hierarchical decentralized federated learning

Federated learning (FL) has gained attention as a distributed learning paradigm for its data privacy benefits and accelerated convergence through parallel computation. Traditional FL relies on a server-client (SC) architecture, where a central server coordinates multiple clients to train a global model, but this approach faces scalability challenges due to server communication bottlenecks. To overcome this, the ring-all-reduce (RAR) architecture has been introduced, eliminating the central server and achieving bandwidth optimality. However, the tightly coupled nature of RAR's ring topology exposes it to unique Byzantine attack risks not present in SC-based FL. Despite its potential, designing Byzantine-robust RAR-based FL algorithms remains an open problem. To address this gap, we propose BRACE (<u>B</u>yzantine-<u>r</u>obust ring-<u>a</u>ll-redu<u>ce</u>), the first RAR-based FL algorithm to achieve both Byzantine robustness and communication efficiency. We provide theoretical guarantees for the convergence of BRACE under Byzantine attacks, demonstrate its bandwidth efficiency, and validate its practical effectiveness through experiments. Our work offers a foundational understanding of Byzantine-robust RAR-based FL design.

Background Federated learning (FL) enhances network traffic classification (NTC) with significant benefits in privacy, performance, and efficiency. However, the distributed nature of FL exposes NTC models to critical adversarial attacks from byzantine clients. These attacks, such as label flipping (LF) and model poisoning, can severely degrade overall model performance, while backdoor and generative adversarial network (GAN) based attacks can force the model to misclassify specific traffic classes. Securing FL-based NTC is paramount, as these vulnerabilities pose substantial threats to its vital role in network management, quality of service, and threat identification. Methods While various defensive measures for FL exist, they are often ineffective against multiple types of adversarial attacks, and their effectiveness diminishes as the number of attackers increases. To address this gap, this study proposed SHeRAA-FL, a secure framework for FL-based NTC. The framework secures the training process by combining remote attestation scoring, hierarchical training, and adaptive aggregation mechanisms, reinforced with hardware-level security and encrypted communication. We developed and evaluated SHeRAA-FL on public datasets, such as ISCX-VPN 2016 and N-BaIoT, benchmarking it against existing approaches, including weighted averaging, median-mean, trim-mean, Krum, and Multi-Krum. Results The evaluation results show that SHeRAA-FL effectively mitigates the impact of multiple types of adversarial attacks, even in scenarios with multiple attackers. For example, in the LF attack, other approaches recorded a 99.6% accuracy reduction, while SHeRAA-FL only recorded a 5.33% reduction. Moreover, in a normal scenario, the framework produces a model with the highest accuracy of 0.9130, indicating minimal disruption to the FL process.

Federated learning (FL) is recognized as a key enabling technology to provide intelligent services for future wireless networks and industrial systems with delay and privacy guarantees. However, the performance of wireless FL can be significantly degraded by Byzantine attack, such as data poisoning attack, model poisoning attack and free-riding attack. To design the Byzantine-resilient FL paradigm in wireless networks with limited radio resources, we propose a novel communication-efficient robust model aggregation scheme via over-the-air computation (AirComp). This is achieved by applying the Weiszfeld algorithm to obtain the smoothed geometric median aggregation against Byzantine attack. The additive structure of the Weiszfeld algorithm is further leveraged to match the signal superposition property of multiple-access channels via AirComp, thereby expediting the communication-efficient secure aggregation process of FL. Numerical results demonstrate the robustness against Byzantine devices and good learning performance of the proposed approach.

Federated Learning (FL) offers a promising way to train machine learning models collaboratively on decentralized edge devices, addressing key privacy, communication, and regulatory challenges in smart city environments. This survey adopts a narrative approach, guided by systematic review principles such as PRISMA and Kitchenham, to synthesize current FL research in urban contexts. Unlike prior domain-focused surveys, this work introduces a challenge-oriented taxonomy and integrates an explicit analysis of reproducibility, including datasets and deployment artifacts, to assess real-world readiness. The review begins by examining how FL supports the privacy-preserving analysis of environmental and mobility data. It then explores strategies for resource optimization, including load balancing, model compression, and hierarchical aggregation. Applications in anomaly and event detection across power grids, water infrastructure, and surveillance systems are also discussed. In the energy sector, the survey emphasizes the role of FL in demand forecasting, renewable integration, and sustainable logistics. Particular attention is given to security issues, including defenses against poisoning attacks, Byzantine faults, and inference threats. The study identifies ongoing challenges such as data heterogeneity, scalability, resource limitations at the edge, privacy–utility trade-offs, and lack of standardization. Finally, it outlines a structured roadmap to guide the development of reliable, scalable, and sustainable FL solutions for smart cities.

As the Augmented Intelligence of Things (AIoT) advances within vehicle-road coordination systems, challenges related to road traffic data transmission and processing are being increasingly addressed. However, this progress also brings significant risks of privacy data leakage. Federated learning (FL), a distributed machine learning paradigm, effectively safeguards client data privacy by allowing multiple participants to collaboratively train models while keeping their data localized. Despite its benefits, FL faces challenges, such as model parameter leakage and Byzantine attacks. To tackle these issues, this article introduces an anonymous and efficient FL framework for vehicle-road coordination systems (AEFL), designed to ensure a secure and reliable vehicle data transmission process. This architecture incorporates a novel group pairing onion routing protocol, which leverages pairing cryptography principles for hierarchical data encryption. During the routing process, relay group nodes decrypt the corresponding layer, ensuring both data confidentiality and node anonymity. Additionally, a sampling method is proposed to accurately identify Byzantine vehicle nodes, enhancing the precision of FL aggregation without compromising overall model performance. Experimental results show that AEFL outperforms the classic TOR anonymous routing protocol, achieving a 100% message delivery rate more quickly. Under the same conditions, the anonymity of the source node and the destination node improves by 3.9% and 1.9%, respectively. When half of the nodes are compromised, path anonymity can be increased by 24.8%. Furthermore, our framework excels in FL aggregation efficiency, with a Byzantine adversary detection accuracy of up to 99%.

The federated learning (FL) paradigm is well-suited for the field of medical image analysis, as it can effectively cope with machine learning on isolated multi-center data while protecting the privacy of participating parties. However, current research on optimization algorithms in FL often focuses on limited datasets and scenarios, primarily centered around natural images, with insufficient comparative experiments in medical contexts. In this work, we conduct a comprehensive evaluation of several state-of-the-art FL algorithms in the context of medical imaging. We conduct a fair comparison of classification models trained using various FL algorithms across multiple medical imaging datasets. Additionally, we evaluate system performance metrics, such as communication cost and computational efficiency, while considering different FL architectures. Our findings show that medical imaging datasets pose substantial challenges for current FL optimization algorithms. No single algorithm consistently delivers optimal performance across all medical FL scenarios, and many optimization algorithms may under-perform when applied to these datasets. Our experiments provide a benchmark and guidance for future research and application of FL in medical imaging contexts. Furthermore, we propose an efficient and robust method that combines generative techniques using denoising diffusion probabilistic models with label smoothing to augment datasets, widely enhancing the performance of FL on classification tasks across various medical imaging datasets.

In the Internet of things (IoT), the extensive use of IoT devices makes the problem of spectrum sharing among devices increasingly prominent. Spectrum sensing is very significant to promote spectrum efficiency in IoT. However, due to network security and industry privacy issues, it is difficult to obtain large-scale data sets needed for spectrum sensing. Therefore, federated learning (FL) is an effective technique to solve the problems that may be encountered in the establishment of data sets and the problem of data leakage. In this paper, FL is utilized to study the problem of spectrum sensing, and a value evaluation mechanism of IoT devices is proposed to improve the performance of FL and resist poisoning attacks. Simulation shows that the proposed value evaluation mechanism can make the global model of FL converge more quickly and stably, and at the same time it is almost unaffected by malicious nodes when poisoning attacks occur.KeywordsSpectrum sensingFederated learningValue evaluation mechanismPoisoning attack

With advances in the edge computing (EC) and federated learning (FL) technologies in jointcloud, the edge FL service market has emerged recently and it requires trading edge resources between model requesters and data owners to complete FL tasks, which needs to incentivize sufficient data owners to participate in model training tasks. However, the limitations of resource trading and incentive design for edge FL service market have not been well addressed. In this paper, we propose a two-level blockchain-aided resource trading mechanism for encouraging appropriate edge servers to compete for dynamic FL tasks from the market while incentivizing data owners to participate in the FL tasks. At the upper level, we apply the deep learning-based reverse auction to model the dynamics of the task server selection process, with the aim of maximizing the total social welfare of the edge FL service market, where the edge server, as a seller, considers not only the data contribution of edge devices but also the cost of using blockchain when bidding. At the lower level, the edge servers offer rewards in exchange for the data owners’ participation, while the parameter aggregation is completed through the blockchain in a decentralized manner, which improves the FL’s robustness. Then, we utilize the Stackelberg game to model the dynamic process that the data owners compete for the servers’ revenue. We conduct extensive simulation experiments and the experimental results show that the proposed mechanism is able to get maximized social welfare and provide effective insights and strategies for the resource trading in the edge FL market to complete the federated training.

In federated learning (FL), clients collectively train a global machine learning model with their own local data. Without sharing sensitive raw data, each client in FL only sends updated weights to consider privacy and security concerns. Most of existing FL works focus mainly on improving model accuracy and training time, but only a few works focus on FL incentive mechanisms. To build a high performance model after FL training, clients need to provide high quality and large amounts of data. However, in real FL scenarios, high-quality clients are reluctant to participate in FL process without reasonable compensation, because clients are self-interested and other clients can be business competitors. Even participation incurs some cost for contributing to the FL model with their local dataset. To address this problem, we propose TIFF, a novel tokenized incentive mechanism, where tokens are used as a means of paying for the services of providing participants and the training infrastructure. Without payment delays, participation can be monetized as both providers and consumers, which promotes continued long-term participation of high-quality data parties. Additionally, paid tokens are reimbursed to each client as consumers according to our newly proposed metrics (such as token reduction ratio and utility improvement ratio), which keeps clients engaged in FL process as consumers. To measure data quality, accuracy is calculated in training without additional overheads. We leverage historical accuracy records and random exploration to select high-utility participants and to prevent overfitting. Results show that TIFF provides more tokens to normal providers by up to 6.9% and less tokens to malicious providers by up to 18.1%, achieving improvement of the final model accuracy by up to 7.4%, compared to the default approach.

Federated Learning (FL) has emerged as a suitable option for collaborative, user-centric machine learning while protecting sensitive user data. FL differs significantly from traditional centralized frameworks that collect raw data on a central server. FL focuses on collecting model updates generated locally on edge devices. With traditional FL approaches, data must be downloaded to a central server for model training. In contrast, training occurs on the edge and only model updates are sent. This decentralized framework, unlike traditional FL approaches, is ideal for ubiquitous applications—systems woven seamlessly into everyday surroundings like smart homes, advanced mobile devices, and IoT systems—where sensitive data is constantly and automatically generated. In these systems, user privacy is paramount, and advanced methods must be implemented to ensure privacy and system efficacy. This paper discusses the integration of FL into ubiquitous environments, addressing the relevance, advantages, and disadvantages of this approach. I’d like to focus on privacy-preserving methods, but their preservation against data leakage and adversary attacks adds significant value. There are case studies to show the challenges encountered, lessons learned, and the use of FL within privacy-centric ubiquitous systems. In closing this paper, I summarize the key points and underscore the transformational potential of FL for privacy-sensitive, innovative systems. I also promote further research in this area to support its practical relevance. This paper demonstrates that among the many approaches to privacy within pervasive computing, FL is the only one that is practical and scalable.

In order to meet the extremely heterogeneous requirements of the next generation wireless communication networks, research community is increasingly dependent on using machine‐learning solutions for real‐time decision‐making and radio resource management. Traditional machine learning employs fully centralized architecture in which the entire training data is collected at one node for example, cloud server, that significantly increases the communication overheads and also raises severe privacy concerns. Toward this end, a distributed machine‐learning paradigm termed as federated learning (FL) has been proposed recently. In FL, each participating edge device trains its local model by using its own training data. Then, via the wireless channels the weights or parameters of the locally trained models are sent to the central parameter server (PS), that aggregates them and updates the global model. On one hand, FL plays an important role for optimizing the resources of wireless communication networks, on the other hand, wireless communications is crucial for FL. Thus, a “bidirectional” relationship exists between FL and wireless communications. Although FL is an emerging concept, many publications have already been published in the domain of FL and its applications for next generation wireless networks. Nevertheless, we noticed that none of the works have highlighted the bidirectional relationship between FL and wireless communications. Therefore, the purpose of this survey article is to bridge this gap in literature by providing a timely and comprehensive discussion on the interdependency between FL and wireless communications.

The convergence of vehicular technology, artificial intelligence (AI), and distributed computing has catalyzed the emergence of the Internet of Vehicles (IoV) as a cornerstone of next-generation intelligent transportation systems (ITS). By enabling vehicle-to-everything (V2X) communication, IoV supports cooperative perception, real-time decision-making, and autonomous driving. However, the reliance on large-scale, data-driven intelligence in IoV exposes systems to critical challenges, including adversarial poisoning, privacy leakage, identity forgery, and the fragility of centralized learning architectures. Federated Learning (FL) has been proposed as a promising paradigm to alleviate some of these issues by enabling distributed model training without centralizing sensitive vehicular data. Nonetheless, conventional FL remains vulnerable to security and trust limitations, particularly in dynamic vehicular environments. This thesis addresses these challenges by designing secure, privacy-preserving, and scalable FL frameworks that leverage distributed ledger technologies and cutting-edge security mechanisms.The thesis advances knowledge through four interconnected contributions. First, two novel optimization-driven poisoning attack models are introduced: PA-PSOSA and PAPSOGA, which combine particle swarm optimization with simulated annealing and genetic algorithms, respectively. These models demonstrate that even a small poisoning budget can substantially degrade global model utility under black-box and clean-label constraints, highlighting the urgency of robust defenses in vehicular FL. Second, a permissioned blockchain-enabled FL (BCFL) framework is proposed, in which consortium edge nodes running Practical Byzantine Fault Tolerance (PBFT) consensus replace the central aggregator. With blockchain integration and data validation mechanisms, this design ensures identity authentication, verifiable audit trails, and improved resilience against poisoning and Sybil attacks, while maintaining high model accuracy under adversarial conditions. Third, the framework is further enhanced to achieve inference-resistance by integrating secure aggregation (SecAgg) and differential privacy (DP), and lightweight with off-chain commitments. This design significantly reduces ledger storage requirements, increases system throughput, and mitigates inference-based privacy risks. Finally, to overcome the scalability limitations of PBFT-based BCFL, a DAG-enabled FL (DFL) framework is developed. By leveraging parallel validation, utility-score-based tip selection, and reputation-weighted aggregation, this framework significantly improves scalability, reduces communication complexity, and enhances robustness in asynchronous vehicular environments.Together, these contributions articulate a coherent progression from exposing vulnerabilities in vehicular FL to constructing secure, privacy-preserving, and scalable frameworks tailored for IoV ecosystems. The findings demonstrate that interdisciplinary integration of optimization theory, cryptography, differential privacy, and distributed ledger technologies is indispensable for trustworthy vehicular intelligence. Beyond theoretical significance, the proposed frameworks offer practical designs for deployment in safety-critical IoV environments. Future research directions include the integration of zero-knowledge proofs (ZKP) for verifiable privacy, adaptive defenses against evolving adversarial strategies, and experimental validation in real-world vehicular testbeds. Collectively, this thesis establishes a foundation for secure federated intelligence in IoV, contributing to the reliability, efficiency, and trustworthiness of next-generation ITS.

The advancement of healthcare informatization has resulted in the exponential growth of patient data stored across various hospitals, laboratories, and clinical centers, properly integration and analysis of this data and use it for machine learning can help make medical processes more efficient. However, privacy regulations and institutional silos pose substantial barriers to collaborative research and centralized model training. Here, Federated Learning (FL) has surfaced as an innovative distributed learning approach, as it empowers institutions to jointly build models while safeguarding raw data privacy. This review outlines FL’s fundamentals and highlights its applications across multiple healthcare domains, including medical image analysis, clinical outcome prediction, and wearable health monitoring. The fundamental FL designs (horizontal FL, vertical FL, and split FL learning) and privacy-enhancing methods (safe aggregation, homomorphic encryption, and differential privacy) are discussed. Additionally, we also examine recent advances in adaptive privacy mechanisms, asynchronous updates and explainable AI to support clinical integration. The study concludes with a discussion of current limitations and future research directions, such as multimodal FL, personalized modeling, and edge-based computing.

Federated Learning (FL) represents a transformative advancement in Artificial Intelligence that enables decentralized model training across multiple institutions or devices without transferring raw data. This paradigm is particularly significant for sectors such as healthcare, where privacy, security, and compliance are paramount. This review explores the core principles of FL, its architectural framework, and key differentiators such as horizontal and vertical FL, while examining its major applications across domains including healthcare, finance, mobile systems, and robotics. Through a critical analysis of recent studies, the paper highlights FL's potential to enhance data privacy, mitigate bias from heterogeneous datasets, resist cybersecurity threats, and optimize communication efficiency. It also addresses the limitations that challenge FL's broader adoption, such as high computational costs, vulnerability to adversarial attacks, and data inconsistency across nodes. The findings suggest that FL has the potential to reshape the future of AI by enabling collaborative intelligence without compromising data confidentiality. The paper concludes by outlining future directions for FL research, including adaptive aggregation, secure federated algorithms, and energy-efficient frameworks to enable scalable, ethical, and privacy-aware AI systems.