A design study showing how TrustZone and model partitioning could keep deep learning models secret on untrusted phones, with a rough fourfold overhead estimate for a small network.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices
A design study showing how TrustZone and model partitioning could keep deep learning models secret on untrusted phones, with a rough fourfold overhead estimate for a small network.