提出新方法实现高效深度联邦遗忘，防止隐私泄露。
Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstruction
- 通过权重感知回滚与重建，深度清除客户端影响
- 在4个数据集上准确率提升1%-5%，耗时减少12倍
- 适合关注联邦学习隐私安全的研究者
联邦遗忘（FUL）旨在保护隐私，但高计算成本、复杂激励机制及客户端算力差异导致效率低下。现有方法依赖服务器端知识蒸馏，仅移除目标客户端更新，忽略其他客户端贡献中的隐私信息，易引发隐私泄露。本文提出DPUL，一种全新的服务器端遗忘方法，通过三阶段实现深度遗忘：(i) 依据客户端更新幅度筛选高权重参数并回滚；(ii) 利用变分自编码器（VAE）重构并消除低权重参数；(iii) 采用投影技术恢复模型。在四个数据集上的实验表明，DPUL优于现有最优基线，在准确率上提升1%-5%，时间成本降低最多12倍。
原文摘要 · Abstract (English)
Federated Unlearning (FUL) focuses on client data and computing power to offer a privacy-preserving solution. However, high computational demands, complex incentive mechanisms, and disparities in client-side computing power often lead to long times and higher costs. To address these challenges, many existing methods rely on server-side knowledge distillation that solely removes the updates of the target client, overlooking the privacy embedded in the contributions of other clients, which can lead to privacy leakage. In this work, we introduce DPUL, a novel server-side unlearning method that deeply unlearns all influential weights to prevent privacy pitfalls. Our approach comprises three components: (i) identifying high-weight parameters by filtering client update magnitudes, and rolling them back to ensure deep removal. (ii) leveraging the variational autoencoder (VAE) to reconstruct and eliminate low-weight parameters. (iii) utilizing a projection-based technique to recover the model. Experimental results on four datasets demonstrate that DPUL surpasses state-of-the-art baselines, providing a 1%-5% improvement in accuracy and up to 12x reduction in time cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。