Distributed machine learning, and Decentralized Federated Learning in particular, is emerging as an effective solution to cope with the ever-increasing amount of data and the need to process it faster and more reliably. It enables machine learning models to be trained without centralizing user data, which improves data confidentiality and optimizes performance compared with centralized approaches. However, scaling up such systems can have limitations in terms of data and model traceability and security. To address this limitation, the integration of Blockchain has been proposed, forming a global system leveraging Blockchain, called Blockchain Based Decentralized Federated Learning (BDFL), and taking advantage of the benefits of this technology, namely transparency, immutability and decentralization. For the time being, few studies have sought to characterize these BDFL systems, although it seems that they can be broken down into a set of layers (blockchain, interconnection of DFL nodes, client selection, data transmission, consensus management) that could have a major impact on the operation of the BDFL as a whole. The aim of this article is therefore to respond to this limitation by highlighting the different layers existing in the architecture of a BDFL system and the solutions proposed in the literature that can be integrated to optimise both the performance and the security of the system. This could ultimately lead to the design of more secure and efficient architectures with greater resilience to attacks and architectural changes.
The rise of connected and autonomous vehicles (CAVs) within intelligent transportation systems has introduced new demands for real-time, scalable, and privacy-preserving authentication mechanisms. Traditional authentication methods, such as Public Key Infrastructure (PKI), are often insufficient in highly dynamic vehicular environments due to their reliance on static credentials and centralized control. This paper proposes an adaptive and context-aware authentication framework that integrates Edge Artificial Intelligence (AI) with blockchain technology to secure vehicular communication. The framework leverages edge- based AI models to assess driver behavior and contextual signals in real time, generating dynamic trust scores for authentication. These scores are verified and recorded through a permissioned blockchain, ensuring tamper-proof identity validation and decentralized access control. The proposed system addresses key challenges including low latency, dynamic trust evaluation, and conditional privacy. Through detailed architectural design and security analysis, this work highlights the potential of hybrid AI-blockchain models to enhance the security, scalability, and accountability of future vehicular networks.
Wireless body area networks (WBAN) are essential components of intelligent healthcare monitoring techniques. Especially, when the number and datatype inWBANincreases. InWBAN, secure multidimensional data aggregation received a lot of attention. However, the related schemes consume more computational and communication overhead to encrypt/decrypt the multidimensional health reports. In this paper, a blockchain-assisted scalable and secure multidimensional data aggregation scheme is introduced for fog-basedWBAN. The multidimensional health data are efficiently generated, encrypted, and decrypted by using the Paillier cryptosystem. Further, the batch verification method is used to achieve efficient authentication. The proposed system offers significant security attributes with less computation and communication overhead in comparison with competing systems. Further, it supports statistical analyses such as summation and variance to analyze the received health report.
Electronic health records (EHRs) represent an innovative approach to constructing a distributed data analysis framework for managing health data within its original location. The integration of blockchain technology into EHR systems offers substantial improvements in security, privacy, and transparency, thus enhancing overall management efficiency. Our research spanned from January 2017 to December 2022, conducting a meticulous systematic literature review across reputable databases such as Scopus, IEEE Xplore, Springer, PubMed Central, and ScienceDirect. This comprehensive search, finalized in December 2022, utilized stringent inclusion and exclusion criteria to ensure the selection of high‐quality articles, thereby guaranteeing transparency and unbiased results. Through this systematic review, our primary objective was to explore, assess, and analyze the diverse architectures, proposed models, limitations, and future trajectories of blockchain‐enabled EHR systems. Our emphasis was on highlighting blockchain’s adaptability and robustness in healthcare contexts while identifying potential challenges and areas for further investigation. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis guidelines, we scrutinized more than 600 scientific studies, culminating in the selection of 31 articles that met our rigorous inclusion standards. Our technical and architectural evaluations delved into critical aspects such as privacy, security, authentication, availability, data control, storage, and resource consumption. Our research outcomes underscore the effective resolution of security, privacy, and availability concerns in EHRs through blockchain integration. However, we observed potential trade‐offs, including impacts on performance, resource utilization, and regulatory compliance. To address these complexities, we introduce an integrated framework designed to mitigate key challenges and deliver substantial value within this domain.
As machine learning permeates sensitive domains such as healthcare, finance, and government, protecting individual privacy while leveraging large-scale data remains a paramount challenge. Privacy-Preserving Machine Learning (PPML) combines cryptographic techniques, decentralized training paradigms, and data governance policies to enable secure and compliant model development. This paper provides a comprehensive survey of fundamental PPML methods differential privacy, federated learning, homomorphic encryption and examines key data governance frameworks underpinning ethical AI adoption. We analyze technical trade-offs, including privacy-utility balance, scalability, and adversarial resilience. Finally, ongoing research directions and policy implications are discussed, emphasizing interdisciplinary collaboration for trustworthy AI deployment.
The quick progress of 5G networks has allowed for intelligent driving. The primary environment for intelligent driving is provided by vehicular ad hoc networks (VANETs), which relay real-time data and communications between moving vehicles and fixed infrastructure. Since the communication is open-access, the message exchanged is vulnerable to privacy and security attacks. To address with this challenge, several authentication schemes have proposed. Nevertheless, the complexity of current these schemes means that re-authenticating vehicle identities every time they reach a new area of infrastructure coverage significantly hampers the overall network’s efficiency. This paper has proposed a handover authentication, called HAFC scheme based on fog computing to achieve fastly re-authentication of vehicles via secure property transfer among infrastructures (fog servers) for 5G-assisted vehicular blockchain networks. The proposed HAFC scheme consists of both stages namely, initial-authentication stage and handover-authentication stage. In security analysis shows that the proposed HAFC scheme’s vehicle to fog server-for both stages is Computational Diffie-Hellma (CDH)-secure. According to the simulation results, the novel handover authentication stage takes only a fraction of the time required for the first one.
Wilson Valdez, Juan Marcelo Parra-Ullauri, Attila Kertész
The proliferation of Internet of Things (IoT) applications poses formidable challenges in managing data processing, privacy, and security. In response, technologies such as Fog Computing (FC), Blockchain (BC), and Federated Learning (FL) have emerged as promising solutions. Combining these technologies can broaden their scope, and impose novel challenges. This paper conducts a Systematic Literature Review (SLR) to investigate their integration within the IoT domain, systematically evaluating the current state-of-the-art by analyzing 40 papers against 38 extraction criteria, encompassing technical characteristics specific to FC, BC, FL, or their integration. The findings offer insights into the advantages, challenges, opportunities, and limitations of this integration, addressing data processing, privacy, and security concerns in IoT. By filling a research gap and directly examining FC, BC, and FL interoperability across architectural layers, this study contributes to knowledge expansion in the field. This paper proposes a novel framework for implementing FL and BC within FC environments for IoT applications, alongside a comprehensive synthesis of existing literature, distinguishing it from previous research efforts. Furthermore, it offers valuable insights into the current landscape, identifies research needs, and proposes future research directions. The framework and literature synthesis provided allow readers to access customized information on FC-BC-FL integration, aiding in designing and implementing robust IoT solutions.
Due to exponential demand in IoT based healthcare, the demand for robust mechanisms to ensure data privacy, security, and scalability with the increasing dependence on cloud-based healthcare systems is immensely felt. Current approaches to dealing with health-care data in cloud settings lack the potency to tackle challenges emanating from the distribution of non-IID data, dynamic access control requirements, and secure cross-chain data analysis. These methods could not provide a holistic solution to adapt with the heterogeneous nature of healthcare data while maintaining advanced privacy and security levels over the distributed networks. In this way, the present work proposes to offer a secure and scalable protocol that is based on the blockchain for healthcare cloud data samples. It integrates the following four new methodologies: Adaptive Federated Learning for Healthcare Data, Secure Homomorphic Blockchain Encryption, Dynamic Attribute-Based Encryption for Healthcare, and Proof of Healthcare Privacy (PoHP) consensus based cross-chain federated Analytics with Zero Knowledge Protocol (ZKP) for healthcare. AFL-HD would work with optimal model training over the distributed healthcare data and thereby handle the challenges that are non-IID in nature, while reducing the communication overhead by 30-40%. SHBE would ensure a 1.5x improvement in encryption and decryption times and also enable secure computations on encrypted data samples. Thus, DABE-HC enables dynamic access control policy management in blockchains, while ensuring access control precision in excess of 99%, with near-instant policy updating. CCFA-HC supports X-blockchain privacy-preserving analytics, thereby reducing the cross-chain communication overhead by 20-30%. In this protocol, therefore, cloud healthcare data management is made more scalable, secure, and private. It allows tackling challenges in the healthcare domain and gives a holistic solution supporting meaningful and secure, efficient, and collaborative healthcare data processing and analytics across distributed environments. The impact of this work is immense in providing a foundation for the next generation of secure healthcare data systems.
With the development of technology, the connected vehicle has been upgraded from a traditional transport vehicle to an information terminal and energy storage terminal. The data of ICV (intelligent connected vehicles) is the key to organically maximizing their efficiency. However, in the context of increasingly strict global data security supervision and compliance, numerous problems, including complex types of connected vehicle data, poor data collaboration between the IT (information technology) domain and OT (operation technology) domain, different data format standards, lack of shared trust sources, difficulty in ensuring the quality of shared data, lack of data control rights, as well as difficulty in defining data ownership, make vehicle data sharing face a lot of problems, and data islands are widespread. This study proposes FADSF (Fuzzy Anonymous Data Share Frame), an automobile data sharing scheme based on blockchain. The data holder publishes the shared data information and forms the corresponding label storage on the blockchain. The data demander browses the data directory information to select and purchase data assets and verify them. The data demander selects and purchases data assets and verifies them by browsing the data directory information. Meanwhile, this paper designs a data structure Data Discrimination Bloom Filter (DDBF), making complaints about illegal data. When the number of data complaints reaches the threshold, the audit traceability contract is triggered to punish the illegal data publisher, aiming to improve the data quality and maintain a good data sharing ecology. In this paper, based on Ethereum, the above scheme is tested to demonstrate its feasibility, efficiency and security.
Federated Learning (FL) has emerged as a revolutionary machine learning approach, enabling the training of algorithms across decentralized devices or servers while maintaining data privacy. Unlike traditional centralized methods that pool data into a single repository, FL keeps data localized, enhancing the protection of sensitive information and ensuring compliance with privacy standards like GDPR and CCPA. This paradigm shift is particularly relevant in today's data-driven world, where concerns over data breaches and regulatory compliance are paramount. FL allows organizations and individuals to collaboratively train powerful machine learning models without sharing sensitive data. By adopting FL approaches, leveraging distributed data and computing power across different sources while respecting user privacy becomes possible. The architecture of FL involves a central system coordinating updates from multiple sources to improve a global model. Edge devices, such as smartphones or IoT devices, perform local training using their unique datasets. Each edge device trains the model locally, sending only updates (like gradients) to the central server, ensuring sensitive data is never exposed1. Furthermore, privacy-preserving technologies like differential privacy and homomorphic encryption strengthen data confidentiality and compliance with regulations. Differential privacy introduces noise to data or model updates to prevent the reconstruction of individual information, while homomorphic encryption allows computations on encrypted data without decryption1. The rise of 5G networks will significantly enhance FL by reducing latency and improving communication between edge devices and central servers, enabling faster model training and real-time applications. Blockchain technology offers a decentralized and immutable ledger for tracking data usage and model updates, creating a transparent and tamper-proof mechanism, addressing trust issues in federated systems and further strengthening security
Internet of Things (IoT) is currently playing a major role in how intelligent devices are interconnected and deployed to automate services in transport and smart living sectors. However, IoT is facing challenges in terms of data protection and authentication due to the heterogeneous nature of IoT devices that do not exhibit a central authority. It is crucial to provide secure and trustworthy solutions for the increasing demands of decentralized IoT environments. To this end, this research proposes a novel integration of blockchain-technologies in IoT services to enhance security, data integrity, users privacy, system scalability and interoperability of devices. This is done by leveraging smart contracts to enforce authentication, access control and data exchange mechanisms for IoT devices. The proposed approach is verified by the construction and deployment of a smart contract over the Polygon blockchain network in a simulated real-world IoT scenario. The obtained results show that the proposed approach ensures fast and secure authentication in IoT networks by decreasing the risk of unauthorized access and data tampering.
Fatemah H. Alghamedy, Nahla El-Haggar, Albandari Alsumayt, Zeyad M. Alfawaer · 8 authors
The rapid advancement of technology has set higher standards for the next generation of wireless communication networks, known as 6G. These networks go beyond the simple task of connecting devices and aim to establish a self-sustaining system within society. One of the key factors in achieving this goal is the integration of AI services and apps through the Internet of Things (IoT), which will be made possible with the support of 6G technology. The advancement of artificial intelligence (AI) will play a crucial role in enhancing the protocols, architectures, and operations of 6G networks. To achieve collaborative AI in IoT applications, Federated Learning (FL) has emerged as a popular method. FL enables AI training without the need for data sharing, ensuring privacy and security. However, FL also faces challenges, such as the presence of malicious data and the risk of single-point failure. To address these concerns, blockchain technology (BCT) offers a secure and efficient solution. By leveraging blockchain, these issues can be effectively tackled, providing a reliable framework for implementing FL-IoT applications.
The secure sharing and privacy protection of medical data have become pain points for medical data management platforms. Therefore, a secure sharing electronic health record privacy protection method based on blockchain is proposed in the study, aiming to improve data security privacy and ensure absolute ownership of patients' medical data. Attribute encryption and blockchain computing are utilized to construct a data secure sharing model, and zero-knowledge proof and ElGamal encryption algorithms are introduced to further improve the construction of data privacy protection methods. Experimental verification showed that the data secure sharing method proposed in the study has more advantages in terms of production key size and time cost. Compared with other public recognition mechanisms, zero-knowledge proof reduced the average time cost of generating keys by 54.36%. The proposed data privacy protection method had an average increase of 7.73% in protection effectiveness compared to other methods. The results indicate that the data secure sharing and privacy protection methods proposed in the study can improve the overall performance and security of the system while fully ensuring the absolute ownership of patients' data. This method has positive application value in the privacy protection of medical data.
Yuming Tang, Yitian Zhang, Tao Niu, Zhen Li · 7 authors
Federated Learning (FL), as an emergent paradigm in privacy-preserving machine learning, has garnered significant interest from scholars and engineers across both academic and industrial spheres. Despite its innovative approach to model training across distributed networks, FL has its vulnerabilities; the centralized server-client architecture introduces risks of single-point failures. Moreover, the integrity of the global model—a cornerstone of FL—is susceptible to compromise through poisoning attacks by malicious actors. Such attacks and the potential for privacy leakage via inference starkly undermine FL’s foundational privacy and security goals. For these reasons, some participants unwilling use their private data to train a model, which is a bottleneck in the development and industrialization of federated learning. Blockchain technology, characterized by its decentralized ledger system, offers a compelling solution to these issues. It inherently prevents single-point failures and, through its incentive mechanisms, motivates participants to contribute computing power. Thus, blockchain-based FL (BCFL) emerges as a natural progression to address FL’s challenges. This study begins with concise introductions to federated learning and blockchain technologies, followed by a formal analysis of the specific problems that FL encounters. It discusses the challenges of combining the two technologies and presents an overview of the latest cryptographic solutions that prevent privacy leakage during communication and incentives in BCFL. In addition, this research examines the use of BCFL in various fields, such as the Internet of Things and the Internet of Vehicles. Finally, it assesses the effectiveness of these solutions.
Zainab Khalid Mohammad, Salman Bin Yousif, Yunus Bin Yousif
Abstract The metaverse, a virtual multiuser environment, has garnered global attention for its potential to offer deeply immersive and participatory experiences. As this technology matures, it is evolving in tandem with emerging innovations such as Web 3.0, Blockchain, nonfungible tokens, and cryptocurrencies like Bitcoin, which play pivotal roles in the metaverse economy. Robust Bitcoin networks must be modelled for the metaverse environment in Industry 5.0 platforms to ensure the metaverse’s sustained growth and relevance. Industry 5.0 is poised to experience significant economic expansion, driven in large part by the transformative influence of metaverse technology. Researchers have actively explored diverse strategies and approaches to address the unique challenges and opportunities presented by current Bitcoin networks, highlighting the limitless potential for enhancing anonymity and privacy while navigating this exciting digital frontier. By addressing the diverse anonymity and privacy evaluation attributes, the lack of clarity regarding the prioritisation of these attributes and the variability in data, this modelling approach can be categorised as a form of multiple attribute decision-making (MADM). This review seeks to achieve three main objectives: firstly, to identify research gaps, obstacles, and problems within scholarly literature, which is crucial for assessing and modelling Bitcoin networks to succour the metaverse environment of Industry 5.0; secondly, to pinpoint theoretical gaps, proposed solutions, and benchmarking of Bitcoin networks; and thirdly, to offer an overview of the existing validation and evaluation methods employed in the literature. This review introduced a unique taxonomy by intersecting “Bitcoin networks based on blockchain aspects” with “anonymity and privacy development attributes aspect.” It emphasised the study’s significance and innovation. The results illustrate that employing MADM techniques is highly suitable for modelling Bitcoin networks to support the metaverse within the context of Industry 5.0. This thorough review is an invaluable resource for academics and decision-makers, offering perspectives regarding the improvements, applications, and potential directions for evaluating Bitcoin networks to bolster the metaverse environment of Industry 5.0.
Decentralized identity represents an innovative approach based on blockchain to achieve effective identity management. This method utilizes decentralized identifiers and verifiable credentials to enable trusted authentication, free circulation of identity information, and self-sovereign control over identity data functionalities. The current decentralized identity systems rely on entirely anonymous identifiers, lacking robust identity regulation. Furthermore, they face challenges such as identity attribute leakage during verifiable credential presentation and the issuers’ struggle to reliably revoke credentials. To address these issues, efficient and practical schemes have been designed based on BBS signature, zero-knowledge proof, dynamic accumulator, and blockchain technology: one for decentralized identifiers management and the other for verifiable credential privacy protection, both of which are supervised and revocable. The former ensures the privacy of subject identity while achieving regulatability and revocability of identity data by the regulator. The latter facilitates selective disclosure of anonymous credentials and reliable revocation. A security analysis shows that the proposed scheme meets anonymity, non-forgeability, regulatory reliability, and revocability reliability, and offers comprehensive and effective privacy protection measures. The experimental results demonstrate that the algorithms designed operate at a millisecond level, which satisfies the demands of blockchain identity management scenarios.
The application of Artificial Intelligence (AI) in educational analytics has ushered in unprecedented enhancement in student learning prediction, learning at scale, auto-grading, and institution-level decision-making. However, the increased generation and processing of student information precipitate unprecedented concerns in privacy and security, spanning breaches and inference attacks through adversarial manipulations, unauthorized third-party information extraction, and AI model explainability restrictions. In this article, we provide a critical overview of privacy-preserving AI-based educational analytics databases, from state-of-the-art approaches such as Differential Privacy (DP), Federated Learning (FL), Homomorphic Encryption (HE), Secure Multi-Party Computation (SMPC), and Blockchain. Global regulation compliance regimes such as the General Data Protection Regulation (GDPR), the Family Educational Rights and Privacy Act (FERPA), and the California Consumer Privacy Act (CCPA) are reviewed, with the ethical trade-offs and conflicts between utility and privacy preservation laid bare. Projected future directions from Zero-Knowledge Proofs (ZKP) and decentralized AI platforms through hybrid AI-privacy architecture and explainable AI (XAI) are discussed.
Zeng Huang, Ming‐Tian Zhang, Tengfei Liu, Anjia Yang
Federated learning is an important distributed model training technique in Internet of Things (IoT), in which participant selection is a key component that plays a role in improving training efficiency and model accuracy. This module enables a central server to select a subset of participants to perform model training based on data and device information. By doing so, selected participants are rewarded and actively perform model training, while participants that are detrimental to training efficiency and model accuracy are excluded. However, in practice, participants may suspect that the central server may have miscalculated and thus not made the selection honestly. This lack of trustworthiness problem, which can demotivate participants, has received little attention. Another problem that has received little attention is the leakage of participants’ private information during the selection process. We will therefore propose a federated learning framework with auditable participant selection. It supports smart contracts in selecting a set of suitable participants based on their training loss without compromising the privacy. Considering the possibility of malicious campaigning and impersonation of participants, the framework employs commitment schemes and zero-knowledge proofs to counteract these malicious behaviors. Finally, we analyze the security of the framework and conduct a series of experiments to demonstrate that the framework can effectively improve the efficiency of federated learning.
Interest in supporting Federated Learning (FL) using blockchains has grown significantly in recent years. However, restricting access to the trained models only to actively participating nodes remains a challenge even today. To address this concern, we propose a methodology that incentivizes model parameter sharing in an FL setup under Local Differential Privacy (LDP). The nodes that share less obfuscated data under LDP are awarded higher quantum of tokens, which they can later use to obtain session keys for accessing encrypted model parameters updated by the server. If one or more of the nodes do not contribute to the learning process by sharing their data, or share only highly perturbed data, they earn less number of tokens. As a result, such nodes may not be able to read the new global model parameters if required. Local parameter sharing and updating of global parameters are done using the distributed ledger of a permissioned blockchain, namely HyperLedger Fabric (HLF). Being a blockchain-based approach, the risk of a single point of failure is also mitigated. Appropriate chaincodes, which are smart contracts in the HLF framework, have been developed for implementing the proposed methodology. Results of an extensive set of experiments firmly establish the feasibility of our approach.
D. Saveetha, G. Maragatham, Vijayakumar Ponnusamy, Nemanja Zdravković
Blockchain networks serve as a transparent and secure ledger storage solution, yet they remain vulnerable to attacks. There must be some mechanism to protect the blockchain network from attacks. Among various attacks, the Distributed Denial of Service (DDoS) attack is considered severe, which is challenging to detect accurately and reliably. Machine learning techniques are used to detect the attack, which requires exploring all global attack data in a single system, which is difficult in practice. This article proposes a distributed machine learning mechanism called Federated Machine Learning for detecting the presence of DDoS attacks. But in federated machine learning the model itself can be poisoned by the malicious collaborating node which is another problem that this article solves by storing the model in blockchain and by introducing a new reputation-based miner selection procedure. The proposed framework integrates the federation of machine learning within the blockchain network framework for detecting DDoS attacks. Under the integrated framework, miners are used to train the blocks and they also participate in the machine learning training. A dynamic reputation-based miner selection mechanism that can balance exploration and exploitation is proposed for optimal miner selection, which can ensure the high accuracy of the machine learning model and improve the security of blockchain from attacks like DDoS attacks and 51% attacks. The proposed framework is tested with Random Forest, Multilayer Perceptron, and Logistic Regression machine learning algorithms. The proposed mechanism achieved maximum accuracy of 99.1% using random forest model which is superior to the existing mechanism of detection of DDoS attacks.
Weiqi Dai, Jinkai Liu, Yang Zhou, Kim‐Kwang Raymond Choo · 7 authors
While blockchain is known to support open and transparent data exchange, partly due to its nontamperability property, it can also be (ab)used to facilitate the spreading of fake and misleading information or information that was subsequently discredited. Hence, this paper proposes a practical, redactable blockchain framework with a public trapdoor (hereafter referred to as PRBFPT). PRBFPT comprises an editing scheme for adding blocks using a new type of blockchain with a chameleon hash. Specifically, PRBFPT is able to involve all nodes in the blockchain in the editing operations by means of a public trapdoor, without requiring additional trapdoor management by predefined nodes or organizations. PRBFPT is also designed to audit and record the content of each editing operation. In other words, after editing and deleting the original data, PRBFPT can still verify its legitimacy. We also propose a contract-based locked voting scheme to better support voting. We then evaluate the prototype implementation of PRBFPT, whose findings show that the total time consumption of adding modules is at the millisecond level, with a negligible impact on the performance of the original system. In addition, the evaluation findings show that the cost of initiating the special transactions is comparable to the consumption of normal Ethereum transactions and is within a manageable range.