Confidential Computing for AI Workloads: Survey and Best Practices

Microsoft Azure Confidential Computing Team

Abstract

Surveys confidential computing technologies (SGX, SEV, TDX) applied to AI workloads covering secure training, inference, and multi-party computation.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202500031,
  title = {Confidential Computing for AI Workloads: Survey and Best Practices},
  author = {Microsoft Azure Confidential Computing Team},
  year = {2024},
  journal = {Microsoft Research},
  url = {https://www.microsoft.com/en-us/research/publication/confidential-computing-for-ai/},
}