arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16294cs.CRcs.AIcs.CV
收藏

BlockFUL:在区块链联邦学习中实现遗忘

BlockFUL: Enabling Unlearning in Blockchained Federated Learning

Information Security Center, State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(信息安全部,网络与交换技术国家重点实验室,北京邮电大学);Global Big Data Technologies Centre, University of Technology Sydney(大数据技术中心,悉尼大学)

Xiao Liu, Mingyuan Li, Xu Wang, Guangsheng Yu, Wei Ni, Lixiang Li, Haipeng Peng, Renping Liu

AI总结:

提出双链框架 BlockFUL,支持并行与顺序联邦遗忘,并结合梯度上升和重训练方法,降低区块链记录更新及多继承模型遗忘的开销。

摘要:

联邦学习(FL)中的遗忘面临重大挑战,因为模型会随着复杂的继承关系而增长和演进。当采用区块链来确保 FL 的完整性和可追溯性时,这种复杂性进一步加剧:需要编辑多个相互关联的区块链记录并更新所有继承模型,使该过程更加复杂。本文提出 Blockchained Federated Unlearning(BlockFUL),这是一种包含活跃链与归档链的双链结构的新型框架,用于在区块链 FL 中实现遗忘能力。BlockFUL 引入了两种新的遗忘范式,即并行范式和顺序范式,它们可通过基于梯度上升和基于重训练的遗忘方法有效实现。这些方法通过支持高效的共识操作并降低计算成本,增强了跨多个继承模型的遗忘过程。大量实验验证,这些方法有效减少了数据依赖和操作开销,从而在 CIFAR-10 和 Fashion-MNIST 数据集上使用 AlexNet、ResNet18 和 MobileNetV2 模型提升了 BlockFUL 中遗忘继承模型的整体性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑