A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference

arXiv:2304.00083v4 Announce Type: replace
Abstract: 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 Augmented/Virtual Reality, integrity verification of the outsourced ML tasks 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 …

applications arxiv as-a-service cost cs.cr cs.lg deployment domains framework generative integrity led low machine machine learning ml security privacy reality research result security sensitive service validation verification virtual virtual reality