Enhancing Data Provenance and Model Transparency in Federated Learning Systems - A Database Approach

arXiv:2403.01451v1 Announce Type: cross
Abstract: Federated Learning (FL) presents a promising paradigm for training machine learning models across decentralized edge devices while preserving data privacy. Ensuring the integrity and traceability of data across these distributed environments, however, remains a critical challenge. The ability to create transparent artificial intelligence, such as detailing the training process of a machine learning model, has become an increasingly prominent concern due to the large number of sensitive (hyper)parameters it utilizes; thus, it is imperative to …

abstract arxiv challenge cs.cr cs.db cs.lg data database data privacy data provenance decentralized devices distributed edge edge devices environments federated learning integrity learning systems machine machine learning machine learning models paradigm privacy provenance systems traceability training transparency type