CoChat
Sign Up
Cited by 131Blockchain Technology Applications and SecurityPrivacy-Preserving Technologies in DataBlockchain Technology in Education and Learning

Federated learning meets blockchain in decentralized data-sharing: Healthcare use case

Open access
Alsamhi, Saeed Hamood, Myrzashova, Raushan, Hawbani, Ammar, Kumar, Santosh, Srivastava, Sumit, Zhao, Liang, Wei, Xi, Guizan, Mohsen +1 more·2024·IEEE Internet of Things Journal
DOI 10.1109/jiot.2024.3367249
Open this paper in CoChat — free accountOpen PDF

Abstract

In the era of data-driven healthcare, the amalgamation of blockchain and Federated Learning (FL) introduces a paradigm shift towards secure, collaborative, and patient-centric data-sharing. This paper pioneers the exploration of the conceptual framework and technical synergy of FL and blockchain for decentralized data-sharing, aiming to strike a balance between data utility and privacy. FL, a decentralized machine learning paradigm, enables collaborative AI model training across multiple healthcare institutions without sharing raw patient data. Combined with blockchain, a transparent and immutable ledger, it establishes an ecosystem fostering trust, security, and data integrity. The paper elucidates the technical foundations of FL and blockchain, unravelling their roles in reshaping healthcare data-sharing. The paper vividly illustrates the potential impact of this fusion on patient care. The proposed approach preserves patient privacy while granting healthcare providers and researchers access to diversified datasets, ultimately leading to more accurate models and improved diagnoses. The findings underscore the potential acceleration of medical research, improved treatment outcomes, and patient empowerment through data ownership. The synergy of FL and blockchain envisions a healthcare ecosystem that prioritizes individual privacy and propels advancements in medical science.

AI snapshot

Written from the paper’s full text.

TL;DR

The paper proposes a conceptual framework combining federated learning and blockchain for decentralized healthcare data-sharing, using FL to keep raw data local and blockchain for encrypted, immutable transaction records. It illustrates the approach with the Iris dataset and simulated attacks, reporting low attack success rates but no real-world healthcare deployment.

Key findings

  • The FL–blockchain synergy is claimed to enhance security, privacy, interoperability, transparency, and resilience for decentralized data-sharing, addressing the trade-off between data utility and patient privacy.
  • The framework is demonstrated with the Iris dataset: 150 samples from three Iris species, with four features; FL keeps raw data local, while encrypted attributes (sepal length, sepal width, petal length, petal width) are recorded on the blockchain and the species label remains unencrypted metadata.
  • Simulated adversarial Hospital C launched replay, identity masquerade, and man-in-the-middle attacks; defense mechanisms—nonce/hash verification, RSA-based digital signatures with IP verification, and end-to-end encryption—produced low success rates across attack types, with man-in-the-middle slightly higher, as shown in Fig. 8 (no numeric values are given in the text).
  • Healthcare opportunities identified include remote patient monitoring, collaborative research and treatment optimization, and regulatory compliance/consent management for HIPAA, GDPR, and similar rules.

Methods

  • Conceptual framework and architecture integrating FL and blockchain, with algorithms for data retrieval, data transaction, proof-of-work, authorization checks, and adversarial attack simulation.
  • Use case involving hospitals A and B with local datasets; the Iris dataset serves as the primary dataset, FL handles preprocessing/distribution, blockchain stores encrypted attributes, and Hospital C acts as a malicious third party.
  • Evaluation is qualitative/empirical: attack success rates are presented in Fig. 8, and complexity analysis is given for encryption, retrieval \(O(n*d)\), proof-of-work \(O(2^k)\), and authorization \(O(n)\) or \(O(\log n)/O(1)\).

Limitations

  • The paper states challenges including interoperability, scalability, consensus, security, privacy, and data quality; the conclusion also states that “a specific real-world healthcare use case is not presented.”
  • Evident from the text: the evaluation uses the Iris dataset rather than real healthcare data, and no FL model accuracy, clinical outcomes, or deployment results are reported.
  • Evident from the text: attack success rates are described only qualitatively from Fig. 8 without numeric values, and scalability, energy consumption, and regulatory compliance are discussed as challenges rather than empirically tested.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/jiot.2024.3367249

Cites

58 of 58 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 28 cited sources checked · 0 supported · 0 flagged

  • Findingreasoning

    Through these defense mechanisms, our decentralized data-sharing blockchain system demonstrated resilience against the common threats posed by adversarial entities.

    “Through these defense mechanisms, our decentralized datasharing blockchain system demonstrated resilience against the common threats posed by adversarial entities.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The simulated attacks represent common threats to the system.
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.
  • Findingreasoning

    Nonce and hash verification detects replay attacks because a reused nonce value indicates a replay attempt.

    “Replay attacks get detected as the blockchain verifies the nonce and hash values, and a reused nonce value indicates a replay attempt.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.
  • Findingown data

    Our blockchain implementation showcased defense mechanisms against simulated attacks.

    “Against the backdrop of these simulated attacks, our blockchain implementation showcased several defense mechanisms:”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The simulated attacks represent common threats to the system.
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.
  • Premisecitation

    Federated learning incorporates differential privacy, introducing statistical noise that makes re-identifying individuals based on shared information exceedingly difficult.

    “FL incorporates privacy-enhancing techniques like differential privacy, introducing statistical noise into data or model updates, rendering re-identifying individuals based on shared information exceedingly tricky.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [58] Bang, Design of personal data protection decentralized model using blockchain and IPFS

      Not checked in the free run.

  • Premisecitation

    Federated Learning enables collaborative AI model training across multiple healthcare institutions without sharing raw patient data.

    “FL, a decentralized machine learning paradigm, enables collaborative AI model training across multiple healthcare institutions without sharing raw patient data.”
    • Also stated in: § I. INTRODUCTION · plain
      “FL, a decentralized Machine Learning (ML) approach that Google [12] pioneered offers a novel paradigm for collaborative model training across a network of data sources without centralizing raw data.”
    • Also stated in: § B. Related work · plain
      “FL allows multiple parties to train an ML model collaboratively without sharing raw data.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [12] McMahan, Communication-efficient learning of deep networks from decentralized data

      Not checked in the free run.

  • Classified as probably not a substantial claim. 49
  • May combine two claims. 42

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingreasoning

    Proof-of-work is inherently computationally intensive, with average time complexity proportional to the difficulty target, typically exponential concerning the number of leading zeros required in the hash output.

    “Proof-of-work is inherently designed to be computationally intensive.The complexity is not fixed and is adjusted by the difficulty target D. The average time complexity of finding a valid nonce is proportional to the difficulty target, which is typically exponential concerning the number of leading zeros required in the hash output.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingreasoning

    The total time complexity of the data retrieval algorithm is O(n*d), where n is the number of transactions and d is the decryption time.

    “If n represents the number of transactions and d the decryption time, the total time complexity would be O(n*d), assuming the filter operation's complexity is less than or equal to O(n).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Findingnone given

    The data transaction process involves encryption and signing operations, both considered polynomial time complexity based on the key sizes used for encryption and signing.

    “The data transaction process involves encryption and signing operations.Both operations are considered polynomial time complexity based on the key sizes used for encryption and signing.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingreasoning

    The authorization check has a worst-case time complexity of O(n) if the registry is unsorted, and can be reduced to O(log n) or O(1) if the registry is sorted or hashed.

    “If the registry is unsorted and has n entries, this operation has a worst-case time complexity of O(n).If the registry is sorted or hashed, the time complexity could be reduced to O(log n) or even O(1), respectively.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingreasoning

    The graph in Fig. 8 shows a low success rate for replay attacks, remaining consistently low across multiple attempts.

    “The graph in Fig. 8 shows a low success rate for replay attacks, remaining consistently low across multiple attempts.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Findingnone given

    The complexity of adding a new block involves calculating the hash and performing proof-of-work, which has a complexity of O(2^k) on average, where k is the number of bits required by the difficulty target D.

    “The complexity of adding a new block involves calculating the hash and performing the proof-of-work, which has a complexity of O(2 k ) on average, where k is the number of bits required by the difficulty target D.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingreasoning

    Digital signatures and IP verification thwart identity masquerade attempts.

    “The digital signature verification will fail if Hospital C tries to masquerade as Hospital A or B. Additionally, IP address checks were implemented to add an extra layer of verification, further thwarting identity masquerade attempts.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.

  • May combine two claims.

    Findingown data

    The graph in Fig. 8 suggests that man-in-the-middle attacks have a slightly higher success rate than the other two types but remain relatively low.

    “The graph in Fig. 8 suggests that man-in-the-middle attacks have a slightly higher success rate than the other two types but remain relatively low.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Findingnone given

    The transmission complexity of data transactions is typically considered O(1) in the context of algorithmic analysis.

    “The transmission complexity depends on network factors and is typically considered O(1) in the context of algorithmic analysis.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The graph in Fig. 8 shows that the success rate for identity masquerade attacks is low and does not show a significant increase with more attempts.

    “The graph in Fig. 8 corroborates this: the success rate for identity masquerade attacks is also low and does not show a significant increase with more attempts.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Findingreasoning

    End-to-end encryption ensures that even if an adversary intercepts data in a man-in-the-middle attack, it cannot decrypt or modify it without the corresponding private key.

    “This ensures that even if Hospital C intercepts the data in a man-in-the-middle attack, it cannot decrypt or modify it without the corresponding private key.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.

  • May combine two claims.

    Premisecitation

    Federated learning retains sensitive data locally, reducing the risk of data breaches during transmission.

    “FL significantly augments data security and privacy by retaining sensitive information locally, thereby reducing the risk of data breaches during transmission [56].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [56] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Federated learning enables collaborative model training while preserving data privacy and security.

    “FL presents an innovative approach to ML that prioritizes collaborative model training while preserving data privacy and security [55].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [55] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Federated Learning and blockchain have emerged as promising solutions to address challenges of decentralized data-sharing.

    “Several decentralized data-sharing technologies and techniques, such as Federated Learning (FL) [10] and blockchain [11], have emerged as promising solutions to address these challenges.”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [10] source

      Not checked in the free run.

    • cites [11] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    Combining federated learning and blockchain mitigates risks associated with individual participant failures.

    “Combining both mitigates risks associated with individual participant failures.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The synergy of Federated Learning and blockchain creates an environment of trust and accountability among players by protecting intellectual property rights and promoting openness.

    “It creates an environment of trust and accountability among players by protecting intellectual property rights and promoting openness.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    This paper represents a pioneering effort to integrate Federated Learning and blockchain specifically for decentralized healthcare data-sharing.

    “This paper represents a pioneering effort to integrate these technologies specifically for decentralized healthcare data-sharing.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    The framework's healthcare use case leads to more accurate medical models, personalized treatment options, and improved patient care.

    “This approach leads to more accurate medical models, personalized treatment options, and improved patient care, revolutionizing healthcare.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Premisecitation

    Data-sharing enhances transparency and accountability, acting as a bulwark against corruption and building trust among stakeholders.

    “datasharing enhances transparency and accountability, acting as a bulwark against corruption and building trust among stakeholders [18].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [18] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    Using blockchain in conjunction with federated learning can provide increased security and privacy, while also ensuring a transparent and fair training process.

    “Using blockchain in conjunction with FL can provide increased security and privacy, while also ensuring a transparent and fair training process.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning

    The proposed framework enables healthcare institutions, researchers, and patients to share data securely and efficiently.

    “We propose an innovative framework that enables healthcare institutions, researchers, and patients to share data securely and efficiently.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    Combining federated learning and blockchain ensures interoperable data-sharing mechanisms and a common data usage framework.

    “Combining both ensures interoperable data-sharing mechanisms and a common data usage framework.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The combination of federated learning and blockchain encourages active data contribution.

    “The combination encourages active data contribution.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • May combine two claims.

    Premisecitation

    Consensus algorithms verify data accuracy, fortifying security and control over data access.

    “Furthermore, consensus algorithms verify data accuracy [47], fortifying security and control over data access.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [47] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The integration of Federated Learning and blockchain is poised to revolutionize the healthcare landscape, fostering advancements in research, improving patient care, and ensuring regulatory compliance, all while maintaining a steadfast focus on patient privacy.

    “This integration is poised to revolutionize the healthcare landscape, fostering advancements in research, improving patient care, and ensuring regulatory compliance, all while maintaining a steadfast focus on patient privacy.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The synergy of blockchain and Federated Learning guarantees enhanced security, privacy, and a strong barrier against unwanted access and possible data breaches.

    “The synergy of blockchain and FL strategy guarantees enhanced security, privacy and a strong barrier against unwanted access and possible data breaches.”
    • Also stated in: § A. Motivation and Contributions · hedged
      “This method promises enhanced security and privacy, mitigating risks like unauthorized access and data breaches.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Centralized data-sharing systems have limitations including data privacy and security concerns, interoperability issues, and single points of failure.

    “However, centralized data-sharing systems have limitations, such as data privacy and security concerns [5]interoperability issues [6], and single points of failure [7].”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [5] source

      Not checked in the free run.

    • cites [6] source

      Not checked in the free run.

    • cites [7] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    The privacy-preserving framework ensures patient information's confidentiality and immutability by amalgamating Federated Learning's capability to train models without exposing raw data and blockchain's strength in maintaining data integrity.

    “By amalgamating FL's capability to train models without exposing raw data and blockchain's strength in maintaining data integrity, we ensure patient information's confidentiality and immutability.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    Combining federated learning and blockchain extends control to model updates and data access.

    “Combining FL and blockchain extends this control to model updates and data access.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Blockchain organizes data into immutable and chronological blocks, authenticated through consensus mechanisms among a network of nodes, ensuring its accuracy and timeliness.

    “Functioning as a ledger system, it organizes data into immutable and chronological blocks, authenticated through consensus mechanisms among a network of nodes, ensuring its accuracy and timeliness [50].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [50] Konecný, 2016, Federated learning: Strategies for improving communication efficiency, arXiv:1610.05492

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    The proposed model enhances patient empowerment by allowing them to maintain control over their healthcare data.

    “The proposed model enhances patient empowerment by allowing them to maintain control over their healthcare data.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationnone given

    The proposed model aligns with stringent regulatory requirements while boosting efficiency, transparency, and trust in the healthcare sector.

    “It aligns with stringent regulatory requirements while boosting efficiency, transparency, and trust in the healthcare sector.”
    • Also stated in: § A. Motivation and Contributions · plain
      “Our framework addresses the critical balance between collaborative healthcare research and patient data privacy, aligning with stringent regulatory standards and enhancing transparency and trust in healthcare data-sharing.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Decentralized data-sharing offers increased privacy and security, improved data ownership and control, and enhanced transparency and accountability.

    “In addition, decentralized data-sharing offers several benefits, such as increased privacy and security, improved data ownership and control, and enhanced transparency and accountability [8].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [8] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    Federated learning and blockchain enhance efficient and trustworthy collaboration.

    “FL and blockchain enhance efficient and trustworthy collaboration.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • May combine two claims.

    Interpretationcitation

    Together, federated learning and blockchain create a platform that enhances security, privacy, interoperability, and transparency in healthcare data-sharing.

    “Together, they create a powerful platform that enhances security, privacy, interoperability, and transparency in datasharing in healthcare [62].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [62]

      Not checked in the free run.

    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The proposed paradigm complies with strict regulations and dramatically increases productivity and openness in the healthcare industry.

    “Not only does it comply with strict regulations, but it also dramatically increases productivity and openness in the healthcare industry.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Advanced consensus mechanisms bolster blockchain's resilience, rendering the system less susceptible to malicious attacks or data breaches.

    “Advanced consensus mechanisms bolster this resilience, rendering the system less susceptible to malicious attacks or data breaches [53].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [53] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    Combining federated learning's model updates with blockchain's data record allows both models and data to be verified for authenticity.

    “Combining FL's model updates with blockchain's data record, both models and data can be verified for authenticity.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    Safe, effective, patient-centered data-sharing will speed up medical research, enhance patient care, and accelerate improvements in healthcare.

    “Safe, effective, patient-centered datasharing will speed up medical research, enhance patient care and accelerate improvements in healthcare.”
    • Also stated in: § A. Motivation and Contributions · plain
      “This approach not only enhances patient care and accelerates medical research but also promises greater accuracy in diagnoses, personalized treatment options, and rapid advancements in medical science.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    A notable gap exists in research exploring the synergistic potential of Federated Learning and blockchain for decentralized healthcare data-sharing.

    “While significant progress has been made in investigating FL and blockchain individually in healthcare, a notable gap in research exploring their synergistic potential exists.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The proposed framework combining Federated Learning and blockchain addresses complex challenges related to data security and efficient sharing, ensuring a patient-centric approach.

    “We propose a novel framework combining FL and blockchain for healthcare data-sharing.This synergy addresses complex challenges related to data security and efficient sharing, ensuring a patient-centric approach.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

    Interpretationreasoning

    The combination of blockchain technology and Federated Learning promises to transform the healthcare industry by promoting scientific breakthroughs, enhancing patient care, and guaranteeing legal compliance.

    “The combination of blockchain technology and FL promises to transform the healthcare industry by promoting scientific breakthroughs, enhancing patient care, and guaranteeing legal compliance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    A decentralized approach utilizing Federated Learning and blockchain leverages distributed computing for efficiency and scalability while harnessing blockchain's strengths in immutability and security.

    “Such a decentralized approach leverages distributed computing for efficiency and scalability while harnessing blockchain's strengths in immutability and security.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim. May combine two claims.

    Premisecitation

    Blockchain is a transparent and immutable ledger capable of ensuring data integrity and transparency.

    “Combined with blockchain, a transparent and immutable ledger, it establishes an ecosystem fostering trust, security, and data integrity.”
    • Also stated in: § I. INTRODUCTION · plain
      “blockchain has transcended its financial origins to become a secure and immutable ledger capable of ensuring data integrity and transparency.”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [14] Nakamoto, Bitcoin: A peer-to-peer electronic cash system

      Not checked in the free run.

    • cites [15] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Premisecitation

    The synergy of Federated Learning and blockchain gives stakeholders unparalleled control over data in addition to security.

    “Moreover, the synergy of FL and blockchain gives stakeholders unparalleled control over data in addition to security [17].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [17] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    Blockchain technology enables patients to participate in medical research while actively preserving data ownership.

    “Blockchain technology enables patients to participate in medical research while actively preserving data ownership.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Premisecitation

    Blockchain's essential attributes position it as a pivotal player in the evolution of data-sharing systems, such as Dataspace 4.0 and 6G, offering a pathway to highly secure, efficient, and transparent decentralized data-sharing platforms.

    “Blockchain's essential attributes position it as a pivotal player in the evolution of data-sharing systems, such as Dataspace 4.0 and 6G, offering a pathway to highly secure, efficient, and transparent decentralized data-sharing platforms [52].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [52] Li, Federated optimization in heterogeneous networks

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning

    Our approach uniquely addresses end-to-end data security, from local model training to secure data storage and sharing.

    “Our approach uniquely addresses end-to-end data security, from local model training to secure data storage and sharing, promising substantial improvements in the efficiency and trustworthiness of collaborative datasharing.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    Federated learning with blockchain ensures end-to-end security, from data training to storage and sharing.

    “FL with blockchain ensures end-to-end security, from data training to storage and sharing.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    The proposed paradigm resolves the conventional trade-off between privacy and data-sharing.

    “Our proposed paradigm stands out for resolving the conventional trade-off between privacy and data-sharing.”
    • Also stated in: § A. Motivation and Contributions · boosted
      “Our proposed decentralized data-sharing model effectively resolves the traditional trade-off between sharing and privacy.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    By utilizing federated learning at the data preprocessing stage, the integrity and privacy of the hospital data is maintained.

    “It's worth noting that by utilizing FL at this stage, the integrity and privacy of the hospital data is maintained.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: A local decentralized network for healthcare data-sharing is needed and beneficial.

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    The distributed processing approach is crucial for maintaining the system's integrity, ensuring data privacy, and enabling collaborative model training across various nodes.

    “This distributed processing approach is crucial for maintaining the system's integrity, ensuring data privacy, and enabling collaborative model training across various nodes.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    Each node in the BCFL system operates autonomously within the decentralized infrastructure, conducting computations using its local data.

    “Each node operates autonomously within the decentralized infrastructure, conducting computations using its local data.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisereasoning

    The time complexity for public-key encryption operations on the Iris dataset attributes is polynomial.

    “The time complexity for such operations typically depends on the critical size and the algorithm used, often being polynomial”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Public-key cryptography is secure for encrypting data attributes.

  • May combine two claims.

    Interpretationown data

    The defence strategies are sufficiently robust, and the system can be considered secure against the simulated adversarial actions.

    “This analysis, supported by the empirical data shown in Fig. 8, demonstrates that the defence strategies are sufficiently robust, and the system can be considered secure against the simulated adversarial actions.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationreasoning

    The distributed local computation enhances the reliability of the federated learning models and ensures their functionality even in adverse circumstances.

    “This not only enhances the reliability of the FL models but also ensures their functionality even in adverse circumstances.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The slight increase in man-in-the-middle success rate could be due to the complexity of detecting and preventing active interception compared to the more straightforward detection of replay and identity attacks.

    “This slight increase could be due to the complexity of detecting and preventing active interception compared to the more straightforward detection of replay and identity attacks.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    The local processing at the nodes is complemented by the blockchain, which provides a secure and transparent way to record and validate the model updates contributed by each node.

    “The local processing at the nodes is complemented by the blockchain, which provides a secure and transparent way to record and validate the model updates contributed by each node.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • Classified as probably not a substantial claim.

    Interpretationnone given

    The federated learning framework ensures that processing occurs locally at each node, particularly the computationally intensive model training tasks.

    “The FL framework ensures that processing occurs locally at each node, particularly the computationally intensive model training tasks.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationown data

    The nonce and hash checks, digital signature and IP verification, and end-to-end encryption collectively contribute to the resilience of the blockchain system, effectively mitigating the risk of poisoning attacks.

    “The nonce and hash checks, digital signature and IP verification, and end-to-end encryption collectively contribute to the resilience of the blockchain system, effectively mitigating the risk of poisoning attacks.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    Using blockchain with federated learning may require additional computational resources and coordination between parties and may not always be necessary or practical depending on the specific use case.

    “However, it may also require additional computational resources and coordination between parties and may not always be necessary or practical depending on the specific use case.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    The system effectively detects and prevents replay attempts due to the robust verification process.

    “This indicates the system's effective detection and prevention of replay attempts attributed to the robust verification process.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    Only aggregated updates are exchanged, ensuring data privacy.

    “Only aggregated updates are exchanged, ensuring data privacy.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    Each node in the BCFL network takes on a portion of the computational load, with local data being processed at the edge.

    “Each node in the network takes on a portion of the computational load, with local data being processed at the edge, close to the data sources.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductreasoning

    A reused nonce indicates a replay attempt, which the blockchain is designed to detect.

    “A reused nonce indicates a replay attempt, which the blockchain is designed to detect.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    Shared attributes, rather than the actual data, get recorded on the blockchain, ensuring transparency, security, and consistency.

    “These shared attributes, rather than the actual data, get recorded on the blockchain, ensuring transparency, security, and consistency.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

  • May combine two claims.

    Study design and conductown data

    The system uses RSA-based digital signatures and IP verification to ensure the authenticity of transactions.

    “The system uses RSA-based digital signatures and IP verification to ensure the authenticity of transactions.”
    Quote in the paperSubstantial claim
67 of 67

  • The paper relies on this without support.

    The safe and ethical sharing of private patient data is a crucial challenge when healthcare data is expanding exponentially, and there is an increasing demand for data-driven medical advancements.

    “The safe and ethical sharing of private patient data is a crucial challenge when healthcare data is expanding exponentially , and there is an increasing demand for data-driven medical advancements.”

  • The paper relies on this without support.

    Centralized data-sharing models are increasingly seen as inadequate due to inherent privacy and security limitations, reliance on singular management entities, and accessibility challenges.

    “Centralized data-sharing models, traditionally prevalent, are increasingly seen as inadequate due to their inherent privacy and security limitations, reliance on singular management entities, and accessibility challenges.”

  • The paper relies on this without support.

    Decentralized data-sharing empowers individuals with heightened data privacy control.

    “Secondly, decentralized data-sharing empowers individuals with heightened data privacy control.”

  • The paper relies on this without support.

    Decentralized data-sharing eliminates the need for a central authority to manage data access, permitting individuals to grant access exclusively to trusted parties.

    “It eliminates the need for a central authority to manage data access, permitting individuals to grant access exclusively to trusted parties.”

  • The paper relies on this without support.

    Decentralized data-sharing improves interoperability across diverse systems and organizations by embracing open standards and protocols.

    “Additionally, decentralized data-sharing improves interoperability across diverse systems and organizations.It achieves this by embracing open standards and protocols that streamline data-sharing among distinct platforms and applications.”

  • The paper relies on this without support.

    Decentralized data-sharing enhances transparency by allowing all parties to access and validate shared data, cultivating trust and collaborative potential.

    “Moreover, this decentralized approach enhances transparency by allowing all parties to access and validate shared data, cultivating trust and collaborative potential.”

  • The paper relies on this without support.

    Blockchain technology is a formidable decentralized and distributed data-sharing solution renowned for its robust security and transparency features.

    “Blockchain technology is a formidable decentralized and distributed data-sharing solution renowned for its robust security and transparency features.”

  • The paper relies on this without support.

    Blockchain-based systems facilitate secure data exchange while preserving data integrity using common data structures and cryptographic algorithms.

    “Blockchain-based systems facilitate secure data exchange while preserving data integrity using common data structures and cryptographic algorithms.”

  • The paper relies on this without support.

    Blockchain's transparency ensures all participants maintain a shared, comprehensive view of data and its historical changes.

    “Transparency, another hallmark feature of blockchain, ensures all participants maintain a shared, comprehensive view of data and its historical changes.”

  • The paper relies on this without support.

    Blockchain's transparency fosters trust among parties, promotes accountability, and ensures compliance.

    “This heightened transparency fosters trust among parties, promotes accountability, and ensures compliance.”

  • The paper relies on this without support.

    Blockchain's resilience guarantees data availability despite system failures or network disruptions.

    “Furthermore, blockchain's resilience factor is crucial in decentralized data-sharing by guaranteeing data availability despite system failures or network disruptions.”

  • The paper relies on this without support.

    Blockchain offers secure and transparent data recording and sharing capabilities, enhances efficiency, accountability, and transparency, and presents novel solutions to industry-specific challenges.

    “It offers secure and transparent data recording and sharing capabilities, enhances efficiency, accountability, and transparency, and presents novel solutions to industry-specific challenges.”

  • The paper relies on this without support.

    Blockchain's decentralization guarantees that no single entity controls the network.

    “Blockchain's decentralization guarantees that no single entity controls the network.”

  • The paper relies on this without support.

    Blockchain's core feature is the distribution of processing among the network of nodes, which guarantees that the system is resilient to attacks, strong, and able to unite different people when trust is lacking.

    “Blockchain technology's core feature is the distribution of processing among the network of nodes.It guarantees that the system is resilient to attacks, strong, and able to unite different people when trust is lacking.”

  • The paper relies on this without support.

    Blockchain provides a secure, transparent ledger for recording transactions and maintaining data integrity.

    “Blockchain complements this by providing a secure, transparent ledger for recording transactions and maintaining data integrity.”

  • The paper relies on this without support.

    IPFS functions as a distributed file system where data is saved among several nodes.

    “Instead of depending on a single server, IPFS functions as a distributed file system where data is saved among several nodes.”

  • The paper relies on this without support.

    IPFS ensures data integrity and minimizes redundancy by assigning a unique hash to each piece of data based on its content.

    “Using a content-addressed architecture, IPFS ensures data integrity and minimizes redundancy by assigning a unique hash to each piece of data depending on its content.”

  • The paper relies on this without support.

    IPFS has improved resilience, making the system resistant to failures.

    “Because the data is spread across several nodes, IPFS has improved resilience, making the system resistant to failures.”

  • The paper relies on this without support.

    Blockchain improves security by guaranteeing data confidentiality and limiting unwanted access.

    “Blockchain improves security by guaranteeing data confidentiality and limiting unwanted access.”

  • The paper relies on this without support.

    Data immutability offers a solid basis for healthcare data exchange inside the local network because it cannot be changed once stored on the blockchain.

    “Data immutability is a significant advantage as it offers a solid basis for healthcare data exchange inside the local network since it cannot be changed once data is stored on the blockchain.”

  • The paper relies on this without support.

    A local decentralized network for healthcare data-sharing is needed and beneficial.

    “The community that the local decentralized network in healthcare serves benefits greatly.First, it allows hospitals, researchers, and patients to safely and effectively share medical data, improving patient care.”

  • The paper relies on this without support.

    Hospitals, researchers, and healthcare organizations will participate as nodes.

    “Nodes representing patients, researchers, and healthcare organizations must be put up to create a local, decentralized network for sharing medical data.”

  • The authors state this as an assumption.

    The Iris dataset is suitable for demonstrating the feasibility and effectiveness of the decentralized data-sharing mechanism.

    “Given its rich history in data analysis and ML, the Iris dataset served as an ideal foundation for demonstrating the feasibility and effectiveness of our decentralized data-sharing mechanism.”

  • The paper relies on this without support.

    The simulated attacks represent common threats to the system.

    “Through these defense mechanisms, our decentralized datasharing blockchain system demonstrated resilience against the common threats posed by adversarial entities.”

  • The paper relies on this without support.

    Public-key cryptography is secure for encrypting data attributes.

    “The encryption process used for the Iris dataset attributes, like sepal length and width, is based on public-key cryptography.”
25 of 25

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?

  • Federated learning is essential in healthcare IoT networks for securing sensitive information and as a mechanism to create a sense of security in AI applications across healthcare providers and patients.

    “Consequently, FL is not only essential in healthcare IoT networks for securing sensitive information but also as a mechanism to create a sense of security in AI applications across healthcare providers and patients [19,20].”

    From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [20]

    The Federated Learning section says FL protects sensitive data by keeping it local and that transparency helps establish trust among collaborating parties. The Conclusion describes trust in healthcare data-sharing as a benefit of combining FL with blockchain. Neither passage establishes that FL itself creates a sense of security in AI applications among both healthcare providers and patients. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Conflicting descriptions of FL transmission security

    Minor

    Table III says FL does not inherently address security during transmission, while Table V lists encryption during transmission and storage as an FL security feature.

  • Encrypted Iris attributes omit petal width in the description

    Minor

    The description lists three attributes encrypted for the blockchain, whereas the paper's transaction representation includes a fourth encrypted attribute, petal width.

2 of 2

Cites

Flagged first, then by citations

Research works printed but not linked: 5

  1. 2023, A common data space 4.0 for European manufacturing.” DFA
  2. 2023, Dataspace 4.0
  3. Curry, 2022, Data sharing spaces: The BDVA perspective,” in Designing Data Spaces: The Ecosystem Approach to Competitive Advantage, 365
  4. 10.4337/9781784717766.00019 · DOI · Paper page
  5. Bang, Design of personal data protection decentralized model using blockchain and IPFS, 251

Cited by

Sorted by citations

Related

Authors
Alsamhi, S. H., Myrzashova, R., Hawbani, A., Kumar, S., Srivastava, S., Zhao, L., Wei, X., Guizan, M., & Curry, E.
Affiliations
  • Ollscoil na Gaillimhe – University of Galway (IE)
  • University of Science and Technology of China (CN)
  • Shenyang Aerospace University (CN)
  • International Institute of Information Technology (IN)
  • M.J.P. Rohilkhand University (IN)
ORCID
Venue
IEEE Internet of Things Journal
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2024-06-01
Volume
11
Issue
11
Pages
19602-19615
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
DOI
10.1109/jiot.2024.3367249
OpenAlex
W4391948475
Semantic Scholar
d0455754ac1f9ff5de3bd5ce76f3a38b40322849
Cited by
131
References
56
Citations by year
2026: 48 · 2025: 60 · 2024: 23
FWCI
49.26
Type
journal article
Language
en
Open access
Licence
Locations
IEEE Internet of Things Journal (publishedVersion, cc-by)
Funders
  • Science Foundation Ireland (SFI/12/RC/2289_P2)
  • ANSO Scholarship for Young Talents
  • Natural Science Foundation of Anhui Province (BJ2060000039)
Topics
  • Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Information Systems › Blockchain Technology in Education and Learning
Keywords
federated learning, blockchain, decentralized data sharing, healthcare data privacy, patient data ownership, data integrity, patient empowerment

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.

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