Papers › Crypto-Oriented Neural Architecture Design

Crypto-Oriented Neural Architecture Design

27 Nov 2019arXiv:1911.12322archive 2025-07-28

Avital Shafran, Gil Segev, Shmuel Peleg, Yedid Hoshen

As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techniques for secure computation to address such privacy issues. As generic techniques for secure computation are typically prohibitively ineffective, many efforts focus on optimizing their underlying cryptographic tools. Differently, we propose to optimize the initial design of crypto-oriented neural architectures and provide a novel Partial Activation layer. The proposed layer is much faster for secure computation. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.

PaperPDFCode

Code

tf-encrypted/tf-encrypted mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionDropoutFire ModuleGlobal Average PoolingInverted Residual BlockMax PoolingPointwise ConvolutionReLUResidual ConnectionSoftmaxSqueezeNetXavier Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections