Robustness, Efficiency, or Privacy: Pick Two in Machine Learning

arXiv:2312.14712v2 Announce Type: replace-cross
Abstract: The success of machine learning (ML) applications relies on vast datasets and distributed architectures which, as they grow, present major challenges. In real-world scenarios, where data often contains sensitive information, issues like data poisoning and hardware failures are common. Ensuring privacy and robustness is vital for the broad adoption of ML in public life. This paper examines the costs associated with achieving these objectives in distributed ML architectures, from both theoretical and empirical perspectives. We …

applications architectures arxiv challenges cs.cr cs.dc cs.lg data data poisoning datasets distributed efficiency failures hardware information machine machine learning major poisoning privacy real robustness sensitive sensitive information vast world