GuaranTEE: Towards Attestable and Private ML with CCA

arXiv:2404.00190v1 Announce Type: new
Abstract: Machine-learning (ML) models are increasingly being deployed on edge devices to provide a variety of services. However, their deployment is accompanied by challenges in model privacy and auditability. Model providers want to ensure that (i) their proprietary models are not exposed to third parties; and (ii) be able to get attestations that their genuine models are operating on edge devices in accordance with the service agreement with the user. Existing measures to address these challenges …

arxiv cca challenges cs.cr deployment devices edge edge devices exposed guarantee machine privacy private services third third parties