Privacy preserving layer partitioning for Deep Neural Network models

arXiv:2404.07437v1 Announce Type: new
Abstract: MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on their data. However, ensuring user input privacy and secure inference execution is essential. One of the approaches to protect data privacy and integrity is to use Trusted Execution Environments (TEEs) by enabling execution of programs in secure hardware enclave. Using TEEs can introduce significant performance overhead due …

arxiv cloud cloud computing cloud resources computing cs.cr data domain input machine machine learning ml models network neural network popular privacy privacy preserving private resources running service