# Crypto-Oriented Neural Architecture Design

arXiv: https://arxiv.org/abs/1911.12322 · HTML: https://mlsanity.com/paper/1911.12322/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 5 of 5)

- [Verifiable and Provably Secure Machine Unlearning](https://mlsanity.com/paper/2210.09126/) (2022)
- [Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective](https://mlsanity.com/paper/2101.03042/) (2021)
- [Reducing ReLU Count for Privacy-Preserving CNN Speedup](https://mlsanity.com/paper/2101.11835/) (2021)
- [Securing Neural Networks with Knapsack Optimization](https://mlsanity.com/paper/2304.10442/) (2023)
- [Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations](https://mlsanity.com/paper/2608.27066/) (2026)

## Abstract (arXiv)

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.