Fides: A Generative Framework for Result Validation of Outsourced Machine Learning Workloads via TEE. (arXiv:2304.00083v1 [cs.CR])

The growing popularity of Machine Learning (ML) has led to its deployment in
various sensitive domains, which has resulted in significant research focused
on ML security and privacy. However, in some applications, such as autonomous
driving, integrity verification of the outsourced ML workload is more
critical-a facet that has not received much attention. Existing solutions, such
as multi-party computation and proof-based systems, impose significant
computation overhead, which makes them unfit for real-time applications. We
propose Fides, a novel framework for …

applications attention autonomous autonomous driving computation critical deployment domains driving framework generative integrity led machine machine learning novel party privacy research result security solutions systems validation verification workload workloads