Lasagna: Accelerating secure deep learning inference in SGX-enabled edge cloud

Yuepeng Li, Deze Zeng, Lin Gu, Quan Chen, Song Guo, Albert Zomaya, Minyi Guo

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

20 Citations (Scopus)

Abstract

Edge intelligence has already been widely regarded as a key enabling technology in a variety of domains. Along with the prosperity, increasing concern is raised on the security and privacy of intelligent applications. As these applications are usually deployed on shared and untrusted edge servers, malicious co-located attackers, or even untrustworthy infrastructure providers, may acquire highly security-sensitive data and code (i.e., the pre-trained model). Software Guard Extensions (SGX) provides an isolated Trust Execution Environment (TEE) for task security guarantee. However, we notice that DNN inference performance in SGX is severely affected by the limited enclave memory space due to the resultant frequent page swapping operations and the high enclave call overhead. To tackle this problem, we propose Lasagna, an SGX oriented DNN inference performance acceleration framework without compromising the task security. Lasagna consists of a local task scheduler and a global task balancer to optimize the system performance by exploring the layered-structure of DNN models. Our experiment results show that our layer-aware Lasagna effectively speeds up the well-known DNN inference in SGX by 1.31x-1.97x.

Original languageEnglish
Title of host publicationSoCC 2021 - Proceedings of the 2021 ACM Symposium on Cloud Computing
PublisherAssociation for Computing Machinery, Inc
Pages533-545
Number of pages13
ISBN (Electronic)9781450386388
DOIs
Publication statusPublished - 1 Nov 2021
Event12th Annual ACM Symposium on Cloud Computing, SoCC 2021 - Virtual, Online, United States
Duration: 1 Nov 20214 Nov 2021

Publication series

NameSoCC 2021 - Proceedings of the 2021 ACM Symposium on Cloud Computing

Conference

Conference12th Annual ACM Symposium on Cloud Computing, SoCC 2021
Country/TerritoryUnited States
CityVirtual, Online
Period1/11/214/11/21

Keywords

  • DNN Inference
  • Edge intelligence
  • SGX
  • Task scheduling

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Lasagna: Accelerating secure deep learning inference in SGX-enabled edge cloud'. Together they form a unique fingerprint.

Cite this