Proteus: Preserving Model Confidentiality during Graph Optimizations

arXiv:2404.12512v1 Announce Type: new
Abstract: Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typically involves two parties: the model developers and performance optimizers. The collaboration between the parties often necessitates the model developers exposing the model architecture and computational graph to the optimizers. However, this exposure is undesirable since the model architecture is an important intellectual property, and its innovations require significant investments and expertise. …

architecture arxiv collaboration computational confidentiality cs.cr cs.lg deep learning developers development domains efficiency endeavor exposing graph parties performance