Distributed Learning with Curious and Adversarial Machines. (arXiv:2302.04787v1 [cs.LG])

The ubiquity of distributed machine learning (ML) in sensitive public domain
applications calls for algorithms that protect data privacy, while being robust
to faults and adversarial behaviors. Although privacy and robustness have been
extensively studied independently in distributed ML, their synthesis remains
poorly understood. We present the first tight analysis of the error incurred by
any algorithm ensuring robustness against a fraction of adversarial machines,
as well as differential privacy (DP) for honest machines' data against any
other curious entity. …

adversarial algorithm algorithms analysis applications data data privacy differential privacy distributed domain error machine machine learning machines privacy protect public robustness ubiquity