Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 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

BlockDFL: A Blockchain-based Fully Decentralized Peer-to-Peer Federated Learning Framework (2205.10568v3)

Published 21 May 2022 in cs.DC

Abstract: Federated learning (FL) enables collaborative training of machine learning models without sharing training data. Traditional FL heavily relies on a trusted centralized server. Although decentralized FL eliminates the central dependence, it may worsen the other inherit problems faced by FL such as poisoning attacks and data representation leakage due to insufficient restrictions on the behavior of participants, and heavy communication cost, especially in fully decentralized scenarios, i.e., peer-to-peer (P2P) settings. In this paper, we propose a blockchain-based fully decentralized P2P framework for FL, called BlockDFL. It takes blockchain as the foundation, leveraging the proposed PBFT-based voting mechanism and two-layer scoring mechanism to coordinate FL among peer participants without mutual trust, while effectively defending against poisoning attacks. Gradient compression is introduced to lowering communication cost and prevent data from being reconstructed from transmitted model updates. Extensive experiments conducted on two real-world datasets exhibit that BlockDFL obtains competitive accuracy compared to centralized FL and can defend poisoning attacks while achieving efficiency and scalability. Especially when the proportion of malicious participants is as high as 40%, BlockDFL can still preserve the accuracy of FL, outperforming existing fully decentralized P2P FL frameworks based on blockchain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Integration of blockchain and federated learning for Internet of Things: Recent advances and future challenges. Comput. Secur. 108 (2021), 102355.
  2. Poster: A Reliable and Accountable Privacy-Preserving Federated Learning Framework using the Blockchain. In ACM SIGSAC Conference on Computer and Communications Security. 2561–2563.
  3. Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. In Annual Conference on Neural Information Processing Systems. 119–129.
  4. Miguel Castro and Barbara Liskov. 1999. Practical Byzantine Fault Tolerance. In USENIX Symposium on Operating Systems Design and Implementation. 173–186.
  5. When Machine Learning Meets Blockchain: A Decentralized, Privacy-preserving and Secure Design. In IEEE International Conference on Big Data. 1178–1187.
  6. A Fast Blockchain-Based Federated Learning Framework With Compressed Communications. IEEE J. Sel. Areas Commun. 40, 12 (2022), 3358–3372.
  7. A Fast Blockchain-based Federated Learning Framework with Compressed Communications. IEEE Journal on Selected Areas in Communications 40, 12 (2022), 3358–3372.
  8. Li Deng. 2012. The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine 29, 6 (2012), 141–142.
  9. BAFL: A Blockchain-Based Asynchronous Federated Learning Framework. IEEE Trans. Comput. 71, 5 (2022), 1092–1103.
  10. UCI machine learning repository, 2010. URL http://archive.ics.uci.edu/ml 15 (2011), 22.
  11. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. CoRR abs/2210.17323 (2022). https://doi.org/10.48550/arXiv.2210.17323 arXiv:2210.17323
  12. Model inversion attacks that exploit confidence information and basic countermeasures. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1322–1333.
  13. Algorand: Scaling Byzantine Agreements for Cryptocurrencies. In the Symposium on Operating Systems Principles. 51–68.
  14. GFL: A Decentralized Federated Learning Framework Based On Blockchain. CoRR abs/2010.10996 (2020).
  15. Privacy-Preserving Decentralized Aggregation for Federated Learning. In IEEE Conference on Computer Communications Workshops. 1–6.
  16. An Efficient Blockchain Assisted Reputation Aware Decentralized Federated Learning Framework. IEEE Transactions on Network and Service Management 20, 3 (2023), 2771–2782. https://doi.org/10.1109/TNSM.2022.3231283
  17. Blockchained On-Device Federated Learning. IEEE Communications Letters 24, 6 (2020), 1279–1283.
  18. Learning multiple layers of features from tiny images. (2009).
  19. FedLGA: Toward System-Heterogeneity of Federated Learning via Local Gradient Approximation. IEEE Transactions on Cybernetics (2023), 1–14.
  20. Privacy-Preserving Federated Learning Framework Based on Chained Secure Multiparty Computing. IEEE Internet Things J. 8, 8 (2021), 6178–6186.
  21. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. In International Conference on Learning Representations.
  22. Privacy-Enhanced Federated Learning Against Poisoning Adversaries. IEEE Transactions on Information Forensics and Security 16 (2021), 4574–4588.
  23. FedCoin: A Peer-to-Peer Payment System for Federated Learning. In Federated Learning - Privacy and Incentive. Lecture Notes in Computer Science, Vol. 12500. 125–138.
  24. Communication-Efficient Learning of Deep Networks from Decentralized Data. In the International Conference on Artificial Intelligence and Statistics, Vol. 54. 1273–1282.
  25. FedAPEN: Personalized Cross-silo Federated Learning with Adaptability to Statistical Heterogeneity. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1954–1964.
  26. Biscotti: A Blockchain System for Private and Secure Federated Learning. IEEE Transactions on Parallel and Distributed Systems 32, 7 (2021), 1513–1525.
  27. Reza Shokri and Vitaly Shmatikov. 2015. Privacy-Preserving Deep Learning. In Proceedings of the Conference on Computer and Communications Security. 1310–1321.
  28. Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective. In IEEE Conference on Computer Vision and Pattern Recognition. 9311–9319.
  29. Permissioned Blockchain Frame for Secure Federated Learning. IEEE Communications Letters 26, 1 (2022), 13–17. https://doi.org/10.1109/LCOMM.2021.3121297
  30. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).
  31. FedEdge: Accelerating Edge-Assisted Federated Learning. In Proceedings of the ACM Web Conference 2023. 2895–2904.
  32. AI at the Edge: Blockchain-Empowered Secure Multiparty Learning With Heterogeneous Models. IEEE Internet of Things Journal 7, 10 (2020), 9600–9610.
  33. Against Membership Inference Attack: Pruning is All You Need. In the Joint Conference on Artificial Intelligence. 3141–3147.
  34. DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-Based Incentive. IEEE Transactions on Dependable and Secure Computing 18, 5 (2021), 2438–2455.
  35. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087–38099.
  36. An accuracy-lossless perturbation method for defending privacy attacks in federated learning. In Proceedings of the ACM Web Conference 2022. 732–742.
  37. Communication-efficient and Scalable Decentralized Federated Edge Learning. In the Joint Conference on Artificial Intelligence. 5032–5035.
  38. Byzantine-robust distributed learning: Towards optimal statistical rates. In International Conference on Machine Learning. PMLR, 5650–5659.
  39. Incentive Mechanism for Horizontal Federated Learning Based on Reputation and Reverse Auction. In the Web Conference. 947–956.
  40. A Rate-and-Trust-Based Node Selection Model for Block Transmission in Blockchain Networks. IEEE Internet of Things Journal (2022).
  41. Peiyun Zhang and Mengchu Zhou. 2020. Security and trust in blockchains: Architecture, key technologies, and open issues. IEEE Transactions on Computational Social Systems 7, 3 (2020), 790–801.
  42. iDLG: Improved Deep Leakage from Gradients. CoRR abs/2001.02610 (2020).
  43. PVD-FL: A Privacy-Preserving and Verifiable Decentralized Federated Learning Framework. IEEE Transactions on Information Forensics and Security 17 (2022), 2059–2073.
  44. Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices. IEEE Internet of Things Journal 8, 3 (2021), 1817–1829.
  45. A Blockchain-Based Approach for Saving and Tracking Differential-Privacy Cost. IEEE Internet Things J. 8, 11 (2021), 8865–8882.
  46. Blockchain-empowered Federated Learning: Challenges, Solutions, and Future Directions. ACM Comput. Surv. 55, 11 (2023), 240:1–240:31.
  47. Deep Leakage from Gradients. Advances in Neural Information Processing Systems 32 (2019), 14774–14784.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Zhen Qin (105 papers)
  2. Xueqiang Yan (6 papers)
  3. Mengchu Zhou (32 papers)
  4. Shuiguang Deng (45 papers)
Citations (8)
View on Semantic Scholar

Summary

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

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