Home / Papers / A Taxonomy of Attacks on Federated Learning

A Taxonomy of Attacks on Federated Learning

DOI: 10.1109/MSEC.2020.3039941Semantic Scholar

143 Citations•2021•

Malhar Jere, Tyler Farnan, F. Koushanfar

IEEE Security & Privacy

A taxonomy of recent attacks on federated learning systems is provided and the need for more robust threat modeling in Federated learning environments is detailed.

Abstract

Federated learning is a privacy-by-design framework that enables training deep neural networks from decentralized sources of data, but it is fraught with innumerable attack surfaces. We provide a taxonomy of recent attacks on federated learning systems and detail the need for more robust threat modeling in federated learning environments.