Vessels
Kyungtae Kim, Chung Hwan Kim, Junghwan Rhee, Xiao Yu, Haifeng Chen, Dave Tian, Byoungyoung Lee
Abstract
Deep learning systems on the cloud are increasingly targeted by attacks that attempt to steal sensitive data. Intel SGX has been proven effective to protect the confidentiality and integrity of such data during computation. However, state-of-the-art SGX systems still suffer from substantial performance overhead induced by the limited physical memory of SGX. This limitation significantly undermines the usability of deep learning systems due to their memory-intensive characteristics.
Topics & Concepts
Computer scienceUsabilityCloud computingComputer securityConfidentialityOverhead (engineering)Deep learningEmbedded systemOperating systemHuman–computer interactionArtificial intelligenceAdversarial Robustness in Machine LearningSecurity and Verification in ComputingAdvanced Memory and Neural Computing