.png){kind=icon}
.png){kind=icon}
Return
FastSecNet: An Efficient Cryptographic Framework for Private Neural Network Inference
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2023.3262149.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Private neural network inference has demonstrated great importance in various privacy-critical scenarios. However, the primary challenge remaining in prior works is that the evaluation on encrypted data levies prohibitively high runtime and communication overhead. In this work, we present FastSecNet, an efficient two-party cryptographic framework for private inference in the dealer-based pre-processing setting. Specifically, 1) FastSecNet provides an efficient ReLU protocol for the evalution of non-linear layers, which is built up on a recent advanced cryptographic primitive, function secret sharing (FSS). The core of this construction are an optimized ReLU representation and a customized FSS-based ReLU protocol. 2) For linear layer evaluation, we first propose an efficient PRG-based pre-processing protocol based on the fact that one of the inputs is uniformly random in the offline phase. Then, the online phase only communicates one element and consists of lightweight secret-sharing operations in a ring. Extensive evaluations conducted on 4 real-world datasets and 9 neural network models demonstrate that during the online phase, FastSecNet achieves 14x less runtime and 18x less communication cost compared to the state-of-the-art.
Keywords:
Protocols
Cryptography
Servers
Neural networks
Runtime
Privacy
Generators
Private neural network inference
secure multi-party computation
function secret sharing
Journal
IF:
8
Papers:
5.2K
Citations:
2.3W