论文标题
S3ML：用于机器学习推断的安全服务系统
S3ML: A Secure Serving System for Machine Learning Inference
论文作者
论文摘要
我们提出了S3ML，这是本文中用于机器学习推断的安全服务系统。 S3ML在Intel SGX飞地中运行机器学习模型，以保护用户的隐私。 S3ML设计安全的密钥管理服务，以构建灵活的隐私服务器群集，并提出新颖的SGX感知负载平衡和缩放方法，以满足用户的服务级别目标。我们已经基于Kubernetes实施了S3ML，作为一个低空，高可用和可扩展的系统。我们通过在一系列广泛使用的模型上进行了广泛的实验来证明S3ML的系统性能和有效性。
We present S3ML, a secure serving system for machine learning inference in this paper. S3ML runs machine learning models in Intel SGX enclaves to protect users' privacy. S3ML designs a secure key management service to construct flexible privacy-preserving server clusters and proposes novel SGX-aware load balancing and scaling methods to satisfy users' Service-Level Objectives. We have implemented S3ML based on Kubernetes as a low-overhead, high-available, and scalable system. We demonstrate the system performance and effectiveness of S3ML through extensive experiments on a series of widely-used models.
