The paper

• Attesting Distributional Properties of Training Data for Machine Learning (preprint)
  by Vasisht Duddu, Anudeep Das, Nora Khayata, Hossein Yalame, Thomas Schneider, and N. Asokan

has been accepted for publication at ESORICS 2024 (CORE ranking: A).

It is a collaboration with Vasisht Duddu, Anudeep Das, and N. Asokan from the Secure Systems Group at University of Waterloo. The paper proposes the notion of property attestation using Machine Learning, cryptographic techniques, and a mix of both to demonstrate relevant distributional properties of training data in conjunction with the trained model without revealing the data.