Work

Robust Federated Learning with Multi-Step Aggregation

Year: 2025

Type: article

Abstract: In this paper we address the problem of robust federated learning, where the coordinator needs to robustly aggregate locally trained models to minimize the impact of malicious agents. We start by analyzing the state-of-the-art robust aggregation techniques and highlighting their weaknesses, which we exploit to propose a novel attack strategy. We then counteract the proposed attack with a novel multi-step aggregation technique, which cascades three robust aggregation steps. We provide theoretical results characterizing the robustness of the proposed aggregation, and showing that how it outperforms the state of the art. Additionally, we characterize the convergence of a federated algorithm employing our proposed aggregation. We corroborate our theoretical results with experiments for a classification task.

Source: IFAC-PapersOnLine

DOI: 10.1016/j.ifacol.2025.07.065

Authors: Abbas Pasdar, Changxin Liu, Nicola Bastianello

Institutions: University of Padua, East China University of Science and Technology, KTH Royal Institute of Technology

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4413097600

FWCI:

Cites: 14

Cited by:

Related to: 10