A Taxonomy of Attacks on Federated Learning

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.

Automated summary

Federated learning is a privacy-focused framework for training deep neural networks from decentralized data sources, but it is vulnerable to numerous attacks. A more robust threat modeling is needed to enhance security in federated learning environments.