Attesting Distributional Properties of Training Data for Machine Learning

arXiv:2308.09552v3 Announce Type: replace
Abstract: The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover …

arxiv attributes cs.cr cs.lg data draft frameworks machine machine learning model training regulations regulatory sensitive training training data trustworthiness