From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning

TL;DR

This paper reveals a new privacy vulnerability in Decentralized Federated Learning by demonstrating how attackers can infer network topology solely from model behavior, posing significant privacy risks.

Contribution

It introduces a novel Topology Inference Attack in DFL, categorizes attack types, and provides practical strategies to infer participant relationships from model data.

Findings

Topology can be accurately inferred from model behavior.

Attacks pose significant privacy risks in DFL systems.

Key factors influencing attack success are identified.

Abstract

Federated Learning (FL) is widely recognized as a privacy-preserving Machine Learning paradigm due to its model-sharing mechanism that avoids direct data exchange. Nevertheless, model training leaves exploitable traces that can be used to infer sensitive information. In Decentralized FL (DFL), the topology, defining how participants are connected, plays a crucial role in shaping the model's privacy, robustness, and convergence. However, the topology introduces an unexplored vulnerability: attackers can exploit it to infer participant relationships and launch targeted attacks. This work uncovers the hidden risks of DFL topologies by proposing a novel Topology Inference Attack that infers the topology solely from model behavior. A taxonomy of topology inference attacks is introduced, categorizing them by the attacker's capabilities and knowledge. Practical attack strategies are designed for various scenarios, and experiments are conducted to identify key factors influencing attack success. The results demonstrate that analyzing only the model of each node can accurately infer the DFL topology, highlighting a critical privacy risk in DFL systems. These findings offer insights for improving privacy preservation in DFL environments.