Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BlockFUL: Enabling Unlearning in Blockchained Federated Learning (2402.16294v2)

Published 26 Feb 2024 in cs.CR and cs.AI

Abstract: Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships. This complexity is amplified when blockchain is employed to ensure the integrity and traceability of FL, where the need to edit multiple interlinked blockchain records and update all inherited models complicates the process.In this paper, we introduce Blockchained Federated Unlearning (BlockFUL), a novel framework with a dual-chain structure comprising a live chain and an archive chain for enabling unlearning capabilities within Blockchained FL. BlockFUL introduces two new unlearning paradigms, i.e., parallel and sequential paradigms, which can be effectively implemented through gradient-ascent-based and re-training-based unlearning methods. These methods enhance the unlearning process across multiple inherited models by enabling efficient consensus operations and reducing computational costs. Our extensive experiments validate that these methods effectively reduce data dependency and operational overhead, thereby boosting the overall performance of unlearning inherited models within BlockFUL on CIFAR-10 and Fashion-MNIST datasets using AlexNet, ResNet18, and MobileNetV2 models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Machine unlearning. In 2021 IEEE Symposium on Security and Privacy (SP). IEEE, 141–159.
  2. Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In 2015 IEEE symposium on security and privacy. IEEE, 463–480.
  3. Fast federated machine unlearning with nonlinear functional theory. In International conference on machine learning. PMLR, 4241–4268.
  4. Recommendation unlearning. In Proceedings of the ACM Web Conference 2022. 2768–2777.
  5. Zero-shot machine unlearning. IEEE Transactions on Information Forensics and Security (2023).
  6. BAFL: A blockchain-based asynchronous federated learning framework. IEEE Trans. Comput. 71, 5 (2021), 1092–1103.
  7. Eternal sunshine of the spotless net: Selective forgetting in deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9304–9312.
  8. Adaptive machine unlearning. Advances in Neural Information Processing Systems 34 (2021), 16319–16330.
  9. Federated unlearning: How to efficiently erase a client in fl? arXiv preprint arXiv:2207.05521 (2022).
  10. Building redactable consortium blockchain for industrial Internet-of-Things. IEEE Transactions on Industrial Informatics 15, 6 (2019), 3670–3679.
  11. Redactable blockchain supporting supervision and self-management. In Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security. 844–858.
  12. Blockchained on-device federated learning. IEEE Communications Letters 24, 6 (2019), 1279–1283.
  13. Korbinian Koch and Marcus Soll. 2023. No matter how you slice it: Machine unlearning with SISA comes at the expense of minority classes. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, 622–637.
  14. A blockchain-based decentralized federated learning framework with committee consensus. IEEE Network 35, 1 (2020), 234–241.
  15. Federated unlearning. arXiv preprint arXiv:2012.13891 (2020).
  16. Backdoor defense with machine unlearning. In IEEE INFOCOM 2022-IEEE Conference on Computer Communications. IEEE, 280–289.
  17. The right to be forgotten in federated learning: An efficient realization with rapid retraining. In IEEE INFOCOM 2022-IEEE Conference on Computer Communications. IEEE, 1749–1758.
  18. ScaleSFL: a sharding solution for blockchain-based federated learning. In Proceedings of the Fourth ACM International Symposium on Blockchain and Secure Critical Infrastructure. 95–106.
  19. Umer Majeed and Choong Seon Hong. 2019. FLchain: Federated learning via MEC-enabled blockchain network. In 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE, 1–4.
  20. A survey of machine unlearning. arXiv preprint arXiv:2209.02299 (2022).
  21. Ningxin Su and Baochun Li. 2023. Asynchronous federated unlearning. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1–10.
  22. On the necessity of auditable algorithmic definitions for machine unlearning. In 31st USENIX Security Symposium (USENIX Security 22). 4007–4022.
  23. Federated unlearning via class-discriminative pruning. In Proceedings of the ACM Web Conference 2022. 622–632.
  24. Zhilin Wang and Qin Hu. 2021. Blockchain-based federated learning: A comprehensive survey. arXiv preprint arXiv:2110.02182 (2021).
  25. A redactable blockchain framework for secure federated learning in industrial Internet of Things. IEEE Internet of Things Journal 9, 18 (2022), 17901–17911.
  26. Federated unlearning with knowledge distillation. arXiv preprint arXiv:2201.09441 (2022).
  27. Federated unlearning: Guarantee the right of clients to forget. IEEE Network 36, 5 (2022), 129–135.
  28. SAFA: A semi-asynchronous protocol for fast federated learning with low overhead. IEEE Trans. Comput. 70, 5 (2020), 655–668.
  29. An identity management and authentication scheme based on redactable blockchain for mobile networks. IEEE Transactions on Vehicular Technology 69, 6 (2020), 6688–6698.
  30. Arcane: An efficient architecture for exact machine unlearning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22. 4006–4013.
  31. Ironforge: An open, secure, fair, decentralized federated learning. IEEE Transactions on Neural Networks and Learning Systems (2023).
  32. Enabling attribute revocation for fine-grained access control in blockchain-IoT systems. IEEE Transactions on Engineering Management 67, 4 (2020), 1213–1230.
  33. Federated learning based proactive content caching in edge computing. In 2018 IEEE Global Communications Conference (GLOBECOM). IEEE, 1–6.
  34. Chainsfl: Blockchain-driven federated learning from design to realization. In 2021 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 1–6.
  35. Federated unlearning for on-device recommendation. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 393–401.
Citations (2)
View on Semantic Scholar

Summary

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

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