跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24689 · v1

Stealing Exact Training Data from Other Clients during Federated Learning

首次提交 2026-11-19 00:19
版本更新 2026-11-19 00:19
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Malicious adversaries can employ gradient inversion attacks to reverse-engineer private data using the model updates of a round in Federated Learning. While there have been developments in gradient inversion for text, exact text recovery by a malicious client has so far remained infeasible, as FedAvg entangles the gradient contributions of many clients and obscures the signal of any individual sentence. We introduce a novel attack pipeline that unwinds this entanglement progressively through an iterative loop, in which the gradient contributions of sentences recovered exactly in one round are subtracted from the aggregate, exposing the remaining sentences for recovery in the next iteration. We show, for the first time, exact sentence recovery, with 100% precision, and on aggregates containing up to 4×4\times more tokens than the model's hidden dimension, we recover up to 80.2% of client sentences exactly, a regime where existing attacks recover none exactly.

作者备注:Preprint. 22 pages, 21 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 00:19 · 最新观测版本

Stealing Exact Training Data from Other Clients during Federated Learning

Malicious adversaries can employ gradient inversion attacks to reverse-engineer private data using the model updates of a round in Federated Learning. While there have been developments in gradient inversion for text, exact text recovery by a malicious client has so far remained infeasible, as FedAvg entangles the gradient contributions of many clients and obscures the signal of any individual sentence. We introduce a novel attack pipeline that unwinds this entanglement progressively through an iterative loop, in which the gradient contributions of sentences recovered exactly in one round are subtracted from the aggregate, exposing the remaining sentences for recovery in the next iteration. We show, for the first time, exact sentence recovery, with 100% precision, and on aggregates containing up to 4×4\times more tokens than the model's hidden dimension, we recover up to 80.2% of client sentences exactly, a regime where existing attacks recover none exactly.

查看此版本解读 →查看此版本原文 ↗