Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Secure and Efficient Federated Learning Through Layering and Sharding Blockchain (2104.13130v5)

Published 27 Apr 2021 in cs.CR, cs.AI, cs.IT, and math.IT

Abstract: Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern. However, traditional consensus mechanisms and architectures of blockchain systems face significant challenges in handling large-scale FL tasks, especially on Internet of Things (IoT) devices, due to their substantial resource consumption, limited transaction throughput, and complex communication requirements. To address these challenges, this paper proposes ChainFL, a novel two-layer blockchain-driven FL system. It splits the IoT network into multiple shards within the subchain layer, effectively reducing the scale of information exchange, and employs a Direct Acyclic Graph (DAG)-based mainchain as the mainchain layer, enabling parallel and asynchronous cross-shard validation. Furthermore, the FL procedure is customized to integrate deeply with blockchain technology, and a modified DAG consensus mechanism is designed to mitigate distortion caused by abnormal models. To provide a proof-of-concept implementation and evaluation, multiple subchains based on Hyperledger Fabric and a self-developed DAG-based mainchain are deployed. Extensive experiments demonstrate that ChainFL significantly surpasses conventional FL systems, showing up to a 14% improvement in training efficiency and a threefold increase in robustness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. S. Yuan, B. Cao, M. Peng et al., “ChainsFL: blockchain-driven federated learning from design to realization,” in Proc. IEEE Wireless Commun. Networking Conf., WCNC’21.   Nanjing, China: IEEE, Mar. 2021, pp. 1–6.
  2. L. U. Khan, W. Saad, Z. Han et al., “Federated learning for internet of things: recent advances, taxonomy, and open challenges,” IEEE Commun. Surv. Tutorials, vol. 23, no. 3, pp. 1759–1799, Jun. 2021.
  3. B. McMahan, E. Moore, D. Ramage et al., “Communication-efficient learning of deep networks from decentralized data,” in Proc. Int. Conf. Artif. Intell. Stat., AISTATS’17, Fort Lauderdale, Florida, USA, Apr. 2017, pp. 1273–1282.
  4. M. Cao, L. Zhang, and B. Cao, “Toward on-device federated learning: a direct acyclic graph-based blockchain approach,” IEEE Trans. Neural Netw. Learning Syst., vol. 34, no. 4, pp. 2028–2042, Apr. 2023.
  5. Z. Zhao and G. Joshi, “A dynamic reweighting strategy for fair federated learning,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process, ICASSP’2022.   Singapore: IEEE, May 2022, pp. 8772–8776.
  6. J. Zhu, J. Cao, D. Saxena et al., “Blockchain-empowered federated learning: challenges, solutions, and future directions,” ACM Comput. Surv., vol. 55, no. 11, pp. 1–31, Feb. 2023.
  7. S. Dutta, G. Joshi, S. Ghosh et al., “Slow and stale gradients can win the race: error-runtime trade-offs in distributed SGD,” in Proc. Int. Conf. Artif. Intell. Stat., AISTATS’18.   Playa Blanca, Lanzarote, Canary Islands, Spain: PMLR, Aug. 2018.
  8. C. Xie, S. Koyejo, and I. Gupta, “Asynchronous federated optimization,” arXiv preprint arXiv:1903.03934, pp. 1–15, Dec. 2020.
  9. S. Nakamoto, “Bitcoin: a peer-to-peer electronic cash system,” Aug. 2008. [Online]. Available: https://dx.doi.org/10.2139/ssrn.3440802
  10. H. Kim, J. Park, M. Bennis et al., “Blockchained on-device federated learning,” IEEE Commun. Lett., vol. 24, no. 6, pp. 1279–1283, Jun. 2020.
  11. Y. Lu, X. Huang, Y. Dai et al., “Blockchain and federated learning for privacy-preserved data sharing in industrial IoT,” IEEE Trans. Ind. Inf., vol. 16, no. 6, pp. 4177–4186, Jun. 2020.
  12. B. Cao, Z. Zhang, D. Feng et al., “Performance analysis and comparison of PoW, PoS and DAG based blockchains,” Digit. Commun. Netw., vol. 6, no. 4, pp. 480–485, Nov. 2020.
  13. K. Croman, C. Decker, I. Eyal et al., “On scaling decentralized blockchains,” in Proc. Financial Cryptogr. Data Secur., FC’16, Christ Church, Barbados, 2016, pp. 106–125.
  14. M. Castro and B. Liskov, “Practical byzantine fault tolerance,” in Proc. Symp. Oper. Syst. Des. Implement., OSDI’99, New Orleans, USA, Feb. 1999, pp. 1–14.
  15. S. Zhou, H. Huang, W. Chen et al., “PIRATE: a blockchain-based secure framework of distributed machine learning in 5G networks,” IEEE Netw., vol. 34, no. 6, pp. 84–91, Nov. 2020.
  16. J. Weng, J. Weng, J. Zhang et al., “DeepChain: auditable and privacy-preserving deep learning with blockchain-based incentive,” IEEE Trans. Dependable Secure Comput., vol. 18, no. 5, pp. 2438–2455, Sep. 2021.
  17. Y. Qu, M. P. Uddin, C. Gan et al., “Blockchain-enabled federated learning: a survey,” ACM Comput. Surv., vol. 55, no. 4, pp. 70:1–70:35, Nov. 2022.
  18. M. Shayan, C. Fung, C. J. M. Yoon et al., “Biscotti: a blockchain system for private and secure federated learning,” IEEE Trans. Parallel Distrib. Syst., vol. 32, no. 7, pp. 1513–1525, Jul. 2021.
  19. Z. Zhang, D. Dong, Y. Ma et al., “Refiner: a reliable incentive-driven federated learning system powered by blockchain,” Proc. VLDB Endow., vol. 14, no. 12, pp. 2659–2662, Jul. 2021.
  20. U. Majeed and C. S. Hong, “FLchain: federated learning via MEC-enabled blockchain network,” in Asia-Pacific Netw. Oper. Manag. Symp.: Manag. Cyber-Physical World, APNOMS’19.   Matsue, Japan: IEEE, Sep. 2019, pp. 1–4.
  21. H. Liu, S. Zhang, P. Zhang et al., “Blockchain and federated learning for collaborative intrusion detection in vehicular edge computing,” IEEE Trans. Veh. Technol., vol. 70, no. 6, pp. 6073–6084, Jun. 2021.
  22. H. Jin, X. Dai, J. Xiao et al., “Cross-cluster federated learning and blockchain for internet of medical things,” IEEE Internet Things J., vol. 8, no. 21, pp. 15 776–15 784, Nov. 2021.
  23. B. Cao, Z. Wang, L. Zhang et al., “Blockchain systems, technologies, and applications: a methodology perspective,” IEEE Commun. Surv. Tutorials, vol. 25, no. 1, pp. 353–385, 3st Quart., 2023.
  24. X. Qu, S. Wang, Q. Hu et al., “Proof of federated learning: a novel energy-recycling consensus algorithm,” IEEE Trans. Parallel Distrib. Syst., vol. 32, no. 8, pp. 2074–2085, Aug. 2021.
  25. D. Ongaro and J. Ousterhout, “In search of an understandable consensus algorithm,” in Proc. USENIX Annu. Tech. Conf., USENIX ATC’14, Philadelphia, PA, USA, 2014, pp. 305–319.
  26. D. Huang, X. Ma, and S. Zhang, “Performance analysis of the raft consensus algorithm for private blockchains,” IEEE Trans. Syst. Man Cybern. Syst., vol. 50, no. 1, pp. 172–181, Jan. 2020.
  27. Z. Qu, R. Duan, L. Chen et al., “Context-aware online client selection for hierarchical federated learning,” IEEE Trans. Parallel Distrib. Syst., vol. 33, no. 12, pp. 4353–4367, Dec. 2022.
  28. T. Wang, Y. Liu, X. Zheng et al., “Edge-based communication optimization for distributed federated learning,” IEEE Trans. Netw. Sci. Eng., vol. 9, no. 4, pp. 2015–2024, Jul. 2022.
  29. W. Wu, L. He, W. Lin et al., “SAFA: a semi-asynchronous protocol for fast federated learning with low overhead,” IEEE Trans. Comput., vol. 70, no. 5, pp. 655–668, May 2021.
  30. L. Luu, V. Narayanan, C. Zheng et al., “A secure sharding protocol for open blockchains,” in Proc. ACM. Conf. Computer. Commun. Secur., CCS’16, Vienna, Austria, Oct. 2016, pp. 17–30.
  31. B. Cao, L. Zhang, Y. Li et al., “Intelligent offloading in multi-access edge computing: a state-of-the-art review and framework,” IEEE Commun. Mag., vol. 57, no. 3, pp. 56–62, Mar. 2019.
  32. Y. Li, B. Cao, M. Peng et al., “Direct acyclic graph-based ledger for internet of things: performance and security analysis,” IEEE/ACM Trans. Networking, vol. 28, no. 4, pp. 1643–1656, Aug. 2020.
  33. S. Popov, “The tangle,” IOTA, White paper, Apr. 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:4958428
  34. Y. Du, Z. Wang, J. Li et al., “Blockchain-aided edge computing market: smart contract and consensus mechanisms,” IEEE Trans. on Mobile Comput., vol. 22, no. 6, pp. 3193–3208, Jun. 2023.
  35. J. Benet, “IPFS - content addressed, versioned, P2P file system,” arXiv preprint arXiv:1407.3561, pp. 1–11, Jul. 2014.
  36. “Hyperledger fabric,” Jun. 2023. [Online]. Available: https://github.com/hyperledger/fabric
  37. Y. LeCun, L. Bottou, Y. Bengio et al., “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998.
  38. M. Marcus, B. Santorini, and M. A. Marcinkiewicz, “Building a large annotated corpus of english: the penn treebank,” University of Pennsylvania Department of Computer and Information Science Technical, Tech. Rep. No. MS-CIS-93-87, Oct. 1993.
  39. S. Ji, S. Pan, G. Long et al., “Learning private neural language modeling with attentive aggregation,” in Proc. Int. Jt. Conf. Neural Networks, IJCNN’19.   Budapest, Hungary: IEEE, Jul. 2019, pp. 1–8.
  40. T. Mikolov, S. Kombrink, L. Burget et al., “Extensions of recurrent neural network language model,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process, ICASSP’11.   Prague, Czech Republic: IEEE, Aug. 2011, pp. 5528–5531.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Shuo Yuan (34 papers)
  2. Bin Cao (51 papers)
  3. Yao Sun (80 papers)
  4. Zhiguo Wan (15 papers)
  5. Mugen Peng (82 papers)
Citations (13)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now