Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
As the extension of cloud computing and a foundation of IoT, fog computing is experiencing fast prosperity because of its potential to mitigate some troublesome issues, such as network congestion, latency, and local autonomy. However, privacy issues and the subsequent inefficiency are dragging down the performances of fog computing. The majority of existing works hardly consider a reasonable balance between them while suffering from poisoning attacks. To address the aforementioned issues, we propose a novel blockchain-enabled federated learning (FL-Block) scheme to close the gap. FL-Block allows local learning updates of end devices exchanges with a blockchain-based global learning model, which is verified by miners. Built upon this, FL-Block enables the autonomous machine learning without any centralized authority to maintain the global model and coordinates by using a Proof-of-Work consensus mechanism of the blockchain. Furthermore, we analyze the latency performance of FL-Block and further derive the optimal block generation rate by taking communication, consensus delays, and computation cost into consideration. Extensive evaluation results show the superior performances of FL-Block from the aspects of privacy protection, efficiency, and resistance to the poisoning attack.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The block generation rate was optimized by considering the communication, computation and consensus delays in the blockchain enabled secure edge learning systems [252], [253].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [252]
In the citing paper
“To address the adversarial attacks, the blockchain based decentralized learning was proposed in [252] to enable secure global model aggregation by using a consensus mechanism of blockchain.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [252]
In the citing paper
“Another approach to establish data security and eliminate the trust issues is the deployment of FL on blockchain technology [71]- [73].”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [72]
In the citing paper
“The main advantage brought is the replacement of the central authority with a specially designed decentralized privacy protocol.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [72]
In the citing paper
“To empower FL with this approach, Qu et al. [72] propose to store only the pointer of the global updates on-chain, while a distributed hash table is used to save the data.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [72]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“The classic privacy protection framework, differential privacy [11] with its extensions [12], is leveraged to deal with aggregation privacy.”
BackgroundFederated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766 · cited 1×
“Konecný et al. [36] further presented a variant of federated learning which minimizes the communication cost by uploading a lessened number of local parameters.”
BackgroundPractical techniques for searches on encrypted data
Song, D. X., Wagner, D., & Perrig, A. (2002) · Proceeding 2000 IEEE Symposium on Security and Privacy. S&P 2000 · doi:10.1109/secpri.2000.848445 · Cited by 3,350 · cited 1×
“However, there are potential risks due to the storage of the system’s master key in every end device [18].”
BackgroundMillimeter Wave Channel Modeling and Cellular Capacity Evaluation
Akdeniz, M. R., Liu, Y., Samimi, M. K., Sun, S., Rangan, S., Rappaport, T. S., & Erkip, E. (2014) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2014.2328154 · Cited by 2,476
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761315 · Cited by 1,875 · cited 1×
“Nishio and Yonetani [37] also gave insights on how to select clients in a resource-limited mobile edge computing scenario.”
BackgroundClient Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2018) · arXiv · doi:10.48550/arxiv.1804.08333 · Cited by 1,875 · cited 1×
“Nishio and Yonetani [37] also gave insights on how to select clients in a resource-limited mobile edge computing scenario.”
BackgroundFederated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563 · cited 1×
“Konecný et al. [35] explored the applicability of several current models and thereby devised an extension to address the sparse data issues.”
BackgroundFederated Multi-Task LearningPreprint
Smith, V., Chiang, C.-K., Sanjabi, M., & Talwalkar, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10467 · Cited by 1,320 · cited 2×
“Federated learning is a potentially promising tool, which is proposed as a decentralized learning scheme where the local data are distributed to the data owner [33], [34].”
BackgroundBlockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT
Lu, Y., Huang, X., Dai, Y., Maharjan, S., & Zhang, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2942190 · Cited by 1,245 · cited 1×
“Lu et al. [38] integrated federated learning into the consensus algorithm of the blockchain to save the hash rate.”
BackgroundIn-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
Wang, X., Han, Y., Wang, C., Zhao, Q., Chen, X., & Chen, M. (2019) · IEEE Network · doi:10.1109/mnet.2019.1800286 · Cited by 1,030 · cited 1×
“Federated learning is a potentially promising tool, which is proposed as a decentralized learning scheme where the local data are distributed to the data owner [33], [34].”
BackgroundA Comprehensive Survey on Fog Computing: State-of-the-Art and Research Challenges
Mouradian, C., Naboulsi, D., Yangui, S., Glitho, R. H., Morrow, M. J., & Polakos, P. A. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2771153 · Cited by 1,022 · cited 1×
“F OG COMPUTING, which works as a synthesis of cloud computing and edge computing, is fast booming due to its proficiency in various aspects, such as reducing the latency and congestion of network while enabling autonomous systems [1].”
BackgroundBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2020) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2921755 · Cited by 887 · cited 1×
“The blockchain is introduced to this scenario to eliminate the trust issues here [15].”
BackgroundBlockchained On-Device Federated Learning
Kim, H., Park, J., Bennis, M., & Kim, S.-L. (2018) · arXiv · doi:10.48550/arxiv.1808.03949 · Cited by 882 · cited 1×
“The blockchain is introduced to this scenario to eliminate the trust issues here [15].”
BackgroundECPP: Efficient Conditional Privacy Preservation Protocol for Secure Vehicular Communications
Lu, R., Lin, X., Zhu, H., Ho, P.-H., & Shen, X. (2008) · IEEE INFOCOM 2008 - The 27th Conference on Computer Communications · doi:10.1109/infocom.2008.179 · Cited by 724 · cited 2×
“To address the limitation of prestor-ing lots of anonymous certificates, Lu et al. [13] designed a novel model to achieve conditional privacy.”
MethodFederated Learning: Collaborative Machine Learning without Centralized Training Data
A, A. V., Binny, S., R, J. T., Raj, N., & Thomas, V. (2022) · international journal of engineering technology and management sciences · doi:10.46647/ijetms.2022.v06i05.052 · Cited by 489 · cited 1×
“The federated learning [14], which is a new-merging technology, can achieve efficiency communication by exchanging updates between local models and global models [2].”
BackgroundDistributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2956472 · Cited by 459 · cited 2×
“The federated learning [14], which is a new-merging technology, can achieve efficiency communication by exchanging updates between local models and global models [2].”
BackgroundMethodPseudonym Changing at Social Spots: An Effective Strategy for Location Privacy in VANETs
Lu, R., Lin, X., Luan, T. H., Liang, X., & Shen, X. (2012) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2011.2162864 · Cited by 455 · cited 1×
“Privacy protection attracts an increasing volume of interest from both academia and industry [19], [20].”
BackgroundSelf-citationDesign of Secure User Authenticated Key Management Protocol for Generic IoT Networks
Wazid, M., Das, A. K., Odelu, V., Kumar, N., Conti, M., & Jo, M. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2780232 · Cited by 400 · cited 1×
“To further improve, Tan et al. [22] developed an end device identity authentication protocol of end devices and fog servers without certification, while Wazid et al. [23] proposed another secure authentication and key management scheme to improve key security of the users in IoT scenarios.”
BackgroundA Privacy-Preserving Trust Model Based on Blockchain for VANETs
Lu, Z., Liu, W., Wang, Q., Qu, G., & Liu, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2864189 · Cited by 340 · cited 1×
“In addition, Lu et al. proposed a blockchain-based reputation system and Malik proposed a blockchain-based authentication in [30] and [31], respectively.”
BackgroundAuction Mechanisms in Cloud/Fog Computing Resource Allocation for Public Blockchain Networks
Jiao, Y., Wang, P., Niyato, D., & Suankaewmanee, K. (2019) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2019.2900238 · Cited by 242 · cited 1×
“By using the blockchain, Jiao et al. [27] proposed a novel scheme to manage resource allocation for fog or cloud computing.”
MethodPPFA: Privacy Preserving Fog-Enabled Aggregation in Smart Grid
Lyu, L., Nandakumar, K., Rubinstein, B., Jin, J., Bedo, J., & Palaniswami, M. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2803782 · Cited by 240 · cited 1×
“The classic privacy protection framework, differential privacy [11] with its extensions [12], is leveraged to deal with aggregation privacy.”
BackgroundPrivacy-Preserved Pseudonym Scheme for Fog Computing Supported Internet of Vehicles
Kang, J., Yu, R., Huang, X., & Zhang, Y. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2764095 · Cited by 232 · cited 1×
“From the perspective of anonymity, Kang et al. [21] designed a hybrid model that enhances privacy protection by means of pseudonyms.”
BackgroundHu, P., Ning, H., Qiu, T., Song, H., Wang, Y., & Yao, X. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2659783 · Cited by 230 · cited 1×
“[17] devised a novel identity-based scheme to solve device-to-device and device-to-server communications in fog computing.”
MethodPrivacy-Preserving Reputation Management for Edge Computing Enhanced Mobile Crowdsensing
Ma, L., Liu, X., Pei, Q., & Xiang, Y. (2019) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2018.2825986 · Cited by 160 · cited 1×
“It is essential for the end devices to share the local data to central authorities such as fog servers for global aggregation [4].”
BackgroundSelf-citationProviding Task Allocation and Secure Deduplication for Mobile Crowdsensing via Fog Computing
Ni, J., Zhang, K., Yu, Y., Lin, X., & Shen, X. (2018) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2018.2791432 · Cited by 159 · cited 1×
“In fog computing, the environment is open to access, which poses great challenges from the perspective of privacy protection in real-world applications [16].”
BackgroundPrivacy-Preserving Schemes for Ad Hoc Social Networks: A Survey
Ferrag, M. A., Maglaras, L. A., & Ahmim, A. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2718178 · Cited by 152 · cited 1×
“The uploaded data usually contain some unique identifiers, location information, and trajectories, which may lead to further privacy leakage or potential financial loss [5], [6].”
BackgroundPersonalized Search Over Encrypted Data With Efficient and Secure Updates in Mobile Clouds
Li, H., Liu, D., Dai, Y., Luan, T. H., & Yu, S. (2015) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2015.2511457 · Cited by 132 · cited 1×
“Privacy protection attracts an increasing volume of interest from both academia and industry [19], [20].”
BackgroundSelf-citationMalik, N., Nanda, P., Arora, A., He, X., & Puthal, D. (2018) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom/bigdatase.2018.00099 · Cited by 128 · cited 1×
“In addition, Lu et al. proposed a blockchain-based reputation system and Malik proposed a blockchain-based authentication in [30] and [31], respectively.”
BackgroundData Security and Privacy in Fog Computing
Guan, Y., Shao, J., Wei, G., & Xie, M. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700250 · Cited by 121 · cited 1×
“With existing practice and methodologies, inter-dependencies of network entities can be developed in fog computing for potential promising applications [3].”
MethodSample Selected Extreme Learning Machine Based Intrusion Detection in Fog Computing and MEC
An, X., Zhou, X., Lü, X., Lin, F., & Yang, L. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/7472095 · Cited by 100 · cited 1×
“An et al. [39] devised a learning-based intrusion detection based on the sample-selected extreme learning in fog computing.”
BackgroundPrivacy of Things: Emerging Challenges and Opportunities in Wireless Internet of Things
Qu, Y., Yu, S., Zhou, W., Peng, S., Wang, G., & Xiao, K. (2018) · IEEE Wireless Communications · doi:10.1109/mwc.2017.1800112 · Cited by 100 · cited 2×
“On the other side, privacy protection should not dramatically degrade data utility [7].”
BackgroundSelf-citationOn-Device Federated Learning via Blockchain and its Latency Analysis.
Kim, H., Park, J., Bennis, M., & Kim, S. (2018) · Cited by 99
Rowan, S., Clear, M., Gerla, M., Huggard, M., & McGoldrick, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.02553 · Cited by 88 · cited 1×
“Then, Rowan et al. [28] designed a blockchain-enhanced PKI with an interend device session key establishment protocol to provide privacy protection to device-to-device communications.”
BackgroundA Hybrid Privacy Protection Scheme in Cyber-Physical Social Networks
Qu, Y., Yu, S., Gao, L., Zhou, W., & Peng, S. (2018) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2018.2861775 · Cited by 64 · cited 1×
“The uploaded data usually contain some unique identifiers, location information, and trajectories, which may lead to further privacy leakage or potential financial loss [5], [6].”
BackgroundSelf-citationPrivacy on the Edge: Customizable Privacy-Preserving Context Sharing in Hierarchical Edge Computing
Gu, B., Gao, L., Wang, X., Qu, Y., Jin, J., & Yu, S. (2019) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2019.2933639 · Cited by 59 · cited 1×
“Gu et al. [24] proposed a customizable privacy protection model to enable personalized privacy-preserving data sharing using the Markov decision process.”
MethodSelf-citationSecurity and Privacy of Connected Vehicular Cloud Computing
Li, H., Lu, R., Mišić, J., & Mahmoud, M. M. E. A. (2018) · IEEE Network · doi:10.1109/mnet.2018.8370870 · Cited by 52 · cited 1×
“Nevertheless, these three models require a trusted third party, which is another bottleneck in terms of decentralized privacy protection [25].”
BackgroundPrivacy-Preserving Power Injection Over a Hybrid AMI/LTE Smart Grid Network
Mahmoud, M. M. E. A., Saputro, N., Akula, P. K., & Akkaya, K. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2593453 · Cited by 45 · cited 1×
“If certain privacy protection mechanisms are deployed, more communication resources will be occupied, which will be another bottleneck of fog computing [8], [9].”
BackgroundSecure Certificateless Authentication and Road Message Dissemination Protocol in VANETs
Tan, H., Choi, D., Kim, P., Pan, S., & Chung, I. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/7978027 · Cited by 45 · cited 1×
“To further improve, Tan et al. [22] developed an end device identity authentication protocol of end devices and fog servers without certification, while Wazid et al. [23] proposed another secure authentication and key management scheme to improve key security of the users in IoT scenarios.”
BackgroundEfficient and Privacy-Preserving Proximity Detection Schemes for Social Applications
Zhu, H., Wang, F., Lu, R., Liu, F., Fu, G., & Li, H. (2017) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2766701 · Cited by 37 · cited 1×
“If certain privacy protection mechanisms are deployed, more communication resources will be occupied, which will be another bottleneck of fog computing [8], [9].”
BackgroundA novel broadcast authentication protocol for internet of vehicles
Ruan, N., Li, M., & Li, J. (2016) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-016-0493-9 · Cited by 34 · cited 1×
“Ruan et al. [29] presented an onboard network anonymous authentication protocol.”
BackgroundHu, J., Yang, L., & Hanzo, L. (2017) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2017.2678167 · Cited by 29 · cited 2×
“In this scenario, there is a high demand for real-time communication as network traffic flow undergoes a myriad of instant changes [10].”
BackgroundMethodDecentralized Privacy-Preserving Reputation Management for Mobile Crowdsensing
Ma, L., Pei, Q., Qu, Y., Fan, K., & Lai, X. Q. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-37228-6_26 · Cited by 16 · cited 1×
“The leading advantages of blockchain are decentralization, nontempering, open autonomy, and anonymous traceability [26].”
BackgroundSelf-citationBlockchains Meet Distributed Hash Tables: Decoupling Validation from State StoragePreprint
Bernardini, M., Pennino, D., & Pizzonia, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01935 · Cited by 16 · cited 1×
“In [32], blockchain meets the DHT, which decouples validation from state storage.”
BackgroundAchieve Efficient and Privacy-Preserving Proximity Detection Scheme for Social Applications
Wang, F., Zhu, H., Lu, R., Liu, F., Huang, C., & Li, H. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-319-78813-5_17 · Cited by 15
Cited by
Federated Learning for Internet of Things: A Comprehensive Survey
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Vincent Poor, H. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3075439 · Cited by 1,503
Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges
Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3090430 · Cited by 892
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“To address the adversarial attacks, the blockchain based decentralized learning was proposed in [252] to enable secure global model aggregation by using a consensus mechanism of blockchain.”
MethodA Survey on Federated Learning for Resource-Constrained IoT Devices
Imteaj, A., Thakker, U., Wang, S., Li, J., & Amini, M. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3095077 · Cited by 774
“Furthermore, some prior works [202]–[205] proposed mechanisms to preserve privacy in a blockchain-enabled FL-based IoT environment.”
Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications
Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020) · IEEE Access · doi:10.1109/access.2020.3013541 · Cited by 733
Metadata
- Authors
- Qu, Y., Gao, L., Luan, T. H., Xiang, Y., Yu, S., Li, B., & Zheng, G.
- Affiliations
- Deakin University (AU)
- Xidian University (CN)
- University of Technology Sydney (AU)
- Venue
- IEEE Internet of Things Journal
- Published
- 2020-06
- Volume
- 7
- Issue
- 6
- Pages
- 5171-5183
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W3009627224
- Cited by
- 451
- References
- 44
- Citations by year
- 2026: 26 · 2025: 53 · 2024: 84 · 2023: 90 · 2022: 97 · 2021: 77 · 2020: 24
- FWCI
- 67.80
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Licence
- Locations
- IEEE Internet of Things Journal (publishedVersion)
- Figshare (submittedVersion, cc-by)
- UTS ePRESS (University of Technology Sydney) (submittedVersion)
- Funders
- China Scholarship Council (201708240007)
- 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 › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- fog computing, poisoning attacks, proof-of-work consensus, latency analysis, autonomous machine learning, Internet of Things
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.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.