A Taxonomy of Attacks on Federated Learning
Malhar Jere, Tyler Farnan, Farinaz Koushanfar
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.
Topics & Concepts
Federated learningTaxonomy (biology)Computer scienceDeep learningData scienceComputer securityArtificial intelligenceBotanyBiologyPrivacy-Preserving Technologies in DataAdversarial Robustness in Machine LearningCryptography and Data Security