Decentralized Gradient Descent (D-GD) allows a set of users to perform
collaborative learning without sharing their data by iteratively averaging
local model updates with their neighbors in a network graph. The absence of
direct communication between non-neighbor nodes might lead to the belief that
users cannot infer precise information about the data of others. In this work,
we demonstrate the opposite, by proposing the first attack against D-GD that
enables a user (or set of users) to reconstruct the private data of other users
outside their immediate neighborhood. Our approach is based on a reconstruction
attack against the gossip averaging protocol, which we then extend to handle
the additional challenges raised by D-GD. We validate the effectiveness of our
attack on real graphs and datasets, showing that the number of users
compromised by a single or a handful of attackers is often surprisingly large.
We empirically investigate some of the factors that affect the performance of
the attack, namely the graph topology, the number of attackers, and their
position in the graph.

分布式梯度下降 (D-GD) 允许一组用户在网络图中通过迭代平均本地模型更新与其相邻节点进行协同学习，而无需共享数据。我们提出了针对 D-GD 的第一个攻击，并演示了用户（或一组用户）如何通过回声平均协议的重构攻击来重建其他用户的私有数据，验证了攻击的有效性和对用户数量、攻击者数量及其在图中的位置等因素的影响。