提出去中心化模型遗忘方法，确保删除数据后隐私与性能双保障。
Fully Decentralized Certified Unlearning
- 基于随机游走的梯度更新机制，分步调整模型参数。
- 删除数据后测试准确率降至随机猜测水平（约10%）。
- 适用于无中心协调的分布式系统，适合隐私敏感场景。
机器遗忘旨在响应隐私请求或数据投毒，移除指定数据对训练模型的影响。尽管在集中式和联邦服务器协调场景中已有认证遗忘研究（类似差分隐私保证），但无中心协调的去中心化网络仍研究不足。本文研究固定拓扑下的去中心化网络中的认证遗忘，提出RR-DU方法：在遗忘客户端执行一次投影梯度上升，其他节点对保留数据执行几何分布次数的投影下降，并结合子采样高斯噪声与围绕原始模型的可信区域投影。我们提供：(i) 凸情形下的收敛性保证与非凸情形下的驻点保证；(ii) 基于子采样高斯瑞尼差分隐私（RDP）的客户端视图$(ε,δ)$网络遗忘证书，采用段级子采样；(iii) 删除容量边界，其随遗忘数据与本地数据比例变化，量化了去中心化（网络混合与随机子采样）对隐私-效用权衡的影响。实验表明，在图像基准（MNIST、CIFAR-10）上，RR-DU在满足给定$(ε,δ)$的同时，测试准确率高于去中心化差分隐私基线，且遗忘数据测试准确率降至约10%（随机猜测水平）。
原文摘要 · Abstract (English)
Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) $(\varepsilon,δ)$ network-unlearning certificates on client views via subsampled Gaussian Rényi DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy-utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given $(\varepsilon,δ)$ while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing ($\approx 10\%$).
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。