Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations

arXiv:2406.17548v1 Announce Type: new
Abstract: Regulations increasingly call for various assurances from machine learning (ML) model providers about their training data, training process, and the behavior of resulting models during inference. For better transparency, companies (e.g., Huggingface and Google) have adopted model cards and datasheets which describe different properties of the training datasets and models. In the same vein, we introduce the notion of an inference card to describe the properties of a given inference (e.g., binding output to the …

arxiv assurances behavior call companies cs.cr data datasheets google hardware huggingface machine machine learning process property regulations training training data transparency using