Privacy-Preserving DNN Training with Prefetched Meta-Keys on Heterogeneous Neural Network Accelerators
Qiushi Li, Ju Ren, Yan Zhang, Chengru Song, Yiqiao Liao, Yaoxue Zhang
Abstract
The embedded software may migrate the collected data to the server for DNN computation acceleration, which may compromise privacy. We propose a DNN computation framework that combines TEE and NNA to address the privacy leakage problem. We design an NNA-friendly encryption method that enables NNA to correctly compute the encrypted linear input. Facing the overhead of TEE-NNA interaction, we design a pipeline-based prefetch mechanism that can reduce the TEE interaction overhead. Experimentally, our approach proves to be compatible with a wide range of NPUs and TPUs, and improves the performance by 8-19 times over the TEE scheme.
Topics & Concepts
Instruction prefetchComputer scienceEncryptionArtificial neural networkOverhead (engineering)Embedded systemPipeline (software)ComputationComputer networkOperating systemArtificial intelligenceAlgorithmCacheAdversarial Robustness in Machine LearningCryptography and Data SecurityPrivacy-Preserving Technologies in Data