An Optimized and Scalable Blockchain-Based Distributed Learning Platform for Consumer IoT
Abstract
:1. Introduction
1.1. Challenges of the Typical Intelligent System
1.2. Autonomous Learning
1.3. Decentralized Aggregator
- Blockchain-controlled federated machine learning architecture for intelligent analysis of CIoT data produced in smart home networks.
- An optimal solution for handling substantial local transactions generated in a home.
- An optimized approach to manage the continuous transaction-generated Big Data.
- An effective testbed analysis based on the public Stanford (CARS) dataset.
- Finally, open research issues that present the technical challenges raised in real-life environments.
2. Related Works
3. Decentralized Learning Architecture
3.1. Overview
3.2. Typical Smart Home Network Architecture
3.2.1. Home Appliances Connectivity
3.2.2. Independent App Server
Symbol | Meaning |
Transaction from the weight without/with the digital asset | |
Block generated at | |
BC ledger at GW | |
Transaction destination address | |
Transaction source address | |
Consensus leader for global transactions | |
Consensus leader for the global model | |
Public key with the signature of users | |
User | |
Secret key of | |
Local ML model | |
Global ML model |
3.3. Smart Home Gateway
3.4. Blockchain Network (BCN)
- Peers: The BCN comprises multiple peers (i.e., more than three) to ensure consensus and distributed ledger management [26]. Peers receive the transactions from the GWP and verify the source and credentials for the next processing round. A randomly selected leader leads the validation process through consensus. Similarly, another random peer organizes the local model aggregation services and related consensus sessions (details in consensus). Every peer holds related smart contracts and separate ledgers for global models and IoT transactions.
- Consensus: During consensus, BCN initially creates a consensus session leader panel randomly. A particular leader () from the panel leads global transactions for smart homes, and another leader () handles the global model generation process (details in Section 4.2). One peer can lead only one consensus session at a time. The internal policy of the system controls the creation of leader panels and the synchronization of responsibilities. Based on the PBFT consensus algorithm, leaders collect the maximum number of positive concerns from participating peers before approving the transactions. All global transactions from every GW to BCN are led by and collected by consensus for global transactions: positive voting depends on smart contract validation, which was previously stored by a peer. The leader peer collects all simultaneously approved transactions and affixes them to a new block. The newly generated block is then forwarded to every peer in the network.
- Certificate Authority (CA): The CA is responsible for generating unique certificates and keys for every network component, including users. During transaction execution, peers verify the validation of the source and certificates of the destination devices and users.
4. Technical Details
4.1. Scalability and Ledger Optimization
Algorithm 1: Transaction processing at the GWP. |
4.2. Federated Learning
Local Training
4.3. Differential Privacy
4.4. Normalization Technique
5. Evaluations and Analysis
5.1. Stand-Alone Blockchain Applications
5.2. Prediction Analysis
5.3. Result and Discussion
5.4. Application Challenges and Future Direction
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Caviglione, L.; Wendzel, S.; Mazurczyk, W. The Future of Digital Forensics: Challenges and the Road Ahead. IEEE Secur. Priv. 2017, 15, 12–17. [Google Scholar] [CrossRef]
- Holst, A. Smart Home Report 2021. Available online: https://www.statista.com/topics/2430/smart-homes/ (accessed on 22 November 2023).
- Lee, Y.T.; Hsiao, W.H.; Huang, C.M.; Chou, S.C.T. An integrated cloud-based smart home management system with community hierarchy. IEEE Trans. Consum. Electron. 2016, 62, 1–9. [Google Scholar] [CrossRef]
- Thantharate, P.; Thantharate, A. ZeroTrustBlock: Enhancing Security, Privacy, and Interoperability of Sensitive Data through ZeroTrust Permissioned Blockchain. Big Data Cogn. Comput. 2023, 7, 165. [Google Scholar] [CrossRef]
- Gonzalez-Amarillo, C.; Cardenas-Garcia, C.; Mendoza-Moreno, M.; Ramirez-Gonzalez, G.; Corrales, J.C. Blockchain-IoT Sensor (BIoTS): A Solution to IoT-Ecosystems Security Issues. Sensors 2021, 21, 4388. [Google Scholar] [CrossRef] [PubMed]
- Irwin, D.; Albrecht, J. Smart Homes: Implemented. IEEE Pervasive Comput. 2019, 18, 91–95. [Google Scholar] [CrossRef]
- Mukherjee, A.; Balachandra, M.; Pujari, C.; Tiwari, S.; Nayar, A.; Payyavula, S.R. Unified smart home resource access along with authentication using Blockchain technology. Glob. Transitions Proc. 2021, 2, 29–34. [Google Scholar] [CrossRef]
- Yang, J.; Zou, H.; Jiang, H.; Xie, L. Device-Free Occupant Activity Sensing Using WiFi-Enabled IoT Devices for Smart Homes. IEEE Internet Things J. 2018, 5, 3991–4002. [Google Scholar] [CrossRef]
- Wu, Q.; Chen, X.; Zhou, Z.; Zhang, J. FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring. IEEE Trans. Mob. Comput. 2022, 21, 2818–2832. [Google Scholar] [CrossRef]
- Jung, S.S.; Lee, S.J.; Euom, I.C. Delegation-Based Personal Data Processing Request Notarization Framework for GDPR Based on Private Blockchain. Appl. Sci. 2021, 11, 10574. [Google Scholar] [CrossRef]
- Biswas, S.; Sharif, K.; Li, F.; Latif, Z.; Kanhere, S.S.; Mohanty, S.P. Interoperability and Synchronization Management of Blockchain-Based Decentralized e-Health Systems. IEEE Trans. Eng. Manag. 2020, 67, 1363–1376. [Google Scholar] [CrossRef]
- Arif, S.; Khan, M.A.; Rehman, S.U.; Kabir, M.A.; Imran, M. Investigating Smart Home Security: Is Blockchain the Answer? IEEE Access 2020, 8, 117802–117816. [Google Scholar] [CrossRef]
- Dorri, A.; Kanhere, S.S.; Jurdak, R.; Gauravaram, P. Blockchain for IoT security and privacy: The case study of a smart home. In Proceedings of the 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Kona, HI, USA, 13–17 March 2017; pp. 618–623. [Google Scholar] [CrossRef]
- Lin, C.; He, D.; Kumar, N.; Huang, X.; Vijayakumar, P.; Choo, K.K.R. HomeChain: A Blockchain-Based Secure Mutual Authentication System for Smart Homes. IEEE Internet Things J. 2020, 7, 818–829. [Google Scholar] [CrossRef]
- Khan, M.A.; Abbas, S.; Rehman, A.; Saeed, Y.; Zeb, A.; Uddin, M.I.; Nasser, N.; Ali, A. A Machine Learning Approach for Blockchain-Based Smart Home Networks Security. IEEE Netw. 2021, 35, 223–229. [Google Scholar] [CrossRef]
- Kim, D. A Reverse Sequence Hash Chain-based Access Control for a Smart Home System. In Proceedings of the 2020 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 4–6 January 2020; pp. 1–4. [Google Scholar] [CrossRef]
- McMahan, B.; Moore, E.; Ramage, D.; Hampson, S.; Arcas, B.A.Y. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, 20–22 April 2017; Proceedings of Machine Learning Research. Volume 54, pp. 1273–1282. [Google Scholar]
- Ramanan, P.; Nakayama, K. BAFFLE: Blockchain Based Aggregator Free Federated Learning. In Proceedings of the 2020 IEEE International Conference on Blockchain (Blockchain), Rhodes, Greece, 2–6 November 2020; pp. 72–81. [Google Scholar] [CrossRef]
- Sun, J.; Wu, Y.; Wang, S.; Fu, Y.; Chang, X. Permissioned Blockchain Frame for Secure Federated Learning. IEEE Commun. Lett. 2022, 26, 13–17. [Google Scholar] [CrossRef]
- Otoum, S.; Ridhawi, I.A.; Mouftah, H. Securing Critical IoT Infrastructures With Blockchain-Supported Federated Learning. IEEE Internet Things J. 2022, 9, 2592–2601. [Google Scholar] [CrossRef]
- Zhang, W.; Lu, Q.; Yu, Q.; Li, Z.; Liu, Y.; Lo, S.K.; Chen, S.; Xu, X.; Zhu, L. Blockchain-Based Federated Learning for Device Failure Detection in Industrial IoT. IEEE Internet Things J. 2021, 8, 5926–5937. [Google Scholar] [CrossRef]
- Shen, M.; Wang, H.; Zhang, B.; Zhu, L.; Xu, K.; Li, Q.; Du, X. Exploiting Unintended Property Leakage in Blockchain-Assisted Federated Learning for Intelligent Edge Computing. IEEE Internet Things J. 2021, 8, 2265–2275. [Google Scholar] [CrossRef]
- Qi, J.; Lin, F.; Chen, Z.; Tang, C.; Jia, R.; Li, M. High-quality Model Aggregation for Blockchain-based Federated Learning via Reputation-motivated Task Participation. IEEE Internet Things J. 2022, 9, 18378–18391. [Google Scholar] [CrossRef]
- Ammi, M.; Alarabi, S.; Benkhelifa, E. Customized blockchain-based architecture for secure smart home for lightweight IoT. Inf. Process. Manag. 2021, 58, 102482. [Google Scholar] [CrossRef]
- Keckler, S.W.; Dally, W.J.; Khailany, B.; Garland, M.; Glasco, D. GPUs and the Future of Parallel Computing. IEEE Micro 2011, 31, 7–17. [Google Scholar] [CrossRef]
- Alghamdi, A.; Zhu, J.; Yin, G.; Shorfuzzaman, M.; Alsufyani, N.; Alyami, S.; Biswas, S. Blockchain Empowered Federated Learning Ecosystem for Securing Consumer IoT Features Analysis. Sensors 2022, 22, 6786. [Google Scholar] [CrossRef] [PubMed]
- Biswas, S.; Sharif, K.; Li, F.; Nour, B.; Wang, Y. A Scalable Blockchain Framework for Secure Transactions in IoT. IEEE Internet Things J. 2019, 6, 4650–4659. [Google Scholar] [CrossRef]
- Pappas, C.; Chatzopoulos, D.; Lalis, S.; Vavalis, M. IPLS: A Framework for Decentralized Federated Learning. In Proceedings of the 2021 IFIP Networking Conference (IFIP Networking), Espoo, Finland, 21–24 June 2021; pp. 1–6. [Google Scholar] [CrossRef]
- Erlingsson, U.; Pihur, V.; Korolova, A. RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response. In Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security, Scottsdale, AZ, USA, 3–7 November 2014; Association for Computing Machinery: New York, NY, USA, 2014; pp. 1054–1067. [Google Scholar] [CrossRef]
- Dwork, C.; McSherry, F.; Nissim, K.; Smith, A. Calibrating Noise to Sensitivity in Private Data Analysis. In Theory of Cryptography: Third Theory of Cryptography Conference, TCC 2006, New York, NY, USA, 4–7 March 2006; Springer: Berlin/Heidelberg, Germany, 2006; pp. 265–284. [Google Scholar] [CrossRef]
- Jiang, L.; Lou, X.; Tan, R.; Zhao, J. Differentially Private Collaborative Learning for the IoT Edge. In Proceedings of the Wireless Systems and Networks, EWSN ’19, Beijing, China, 25–27 February 2019. [Google Scholar]
- Krause, J.; Stark, M.; Deng, J.; Fei-Fei, L. 3D Object Representations for Fine-Grained Categorization. In Proceedings of the 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, NSW, Australia, 2–8 December 2013. [Google Scholar]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, Z.; Liu, X.; Shao, X.; Alghamdi, A.; Alrizq, M.; Munir, M.S.; Biswas, S. An Optimized and Scalable Blockchain-Based Distributed Learning Platform for Consumer IoT. Mathematics 2023, 11, 4844. https://doi.org/10.3390/math11234844
Wang Z, Liu X, Shao X, Alghamdi A, Alrizq M, Munir MS, Biswas S. An Optimized and Scalable Blockchain-Based Distributed Learning Platform for Consumer IoT. Mathematics. 2023; 11(23):4844. https://doi.org/10.3390/math11234844
Chicago/Turabian StyleWang, Zhaocheng, Xueying Liu, Xinming Shao, Abdullah Alghamdi, Mesfer Alrizq, Md. Shirajum Munir, and Sujit Biswas. 2023. "An Optimized and Scalable Blockchain-Based Distributed Learning Platform for Consumer IoT" Mathematics 11, no. 23: 4844. https://doi.org/10.3390/math11234844