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 (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms.

翻译：机器学习（ML）的成功伴随着对其可信度的日益关注。多个司法管辖区正在制定机器学习监管框架。其中一项关切是确保模型训练数据在特定敏感属性上具有理想的分布特性。例如，监管草案表明模型训练者需要证明训练数据集具备特定分布特性，如反映人口多样性。我们提出"特性证明"概念，允许证明者（如模型训练者）在不泄露数据的情况下，向验证者（如客户）展示训练数据的相关分布特性。我们提出了一种将特性推断与密码机制相结合的有效混合特性证明方案。