一句话：提出基于类型的优化框架 ZENO，通过隐私/张量类型驱动与系统优化加速零知识神经网络推理，最高提升 8.5 倍。
零知识神经网络借助 zkSNARK 保障神经网络计算的完整性与隐私，但其电路规模达百万级且存在严重的标量级依赖，性能远未达到实用。本文提出基于类型的优化框架 ZENO。首先设计 ZENO 语言构造，在保持高层语义的同时携带隐私与张量等类型信息，以支持更激进的优化；进而提出隐私类型驱动和张量类型驱动的电路优化，并设计面向神经网络推理的系统级优化。实验表明，ZENO 相比当前最优 zkSNARK 神经网络实现取得最高 8.5 倍端到端加速，并将 VGG16 的证明时间从 6 分钟降至 48 秒，使零知识神经网络推理更具实用性。
Zero knowledge Neural Networks draw increasing attention for guaranteeing computation integrity and privacy of neural networks (NNs) based on zero-knowledge Succinct Non-interactive ARgument of Knowledge (zkSNARK) security scheme. However, the performance of zkSNARK NNs is far from optimal due to the million-scale circuit computation with heavy scalar-level dependency. In this paper, we propose a type-based optimizing framework for efficient zero-knowledge NN inference, namely ZENO (ZEro knowledge Neural network Optimizer). We first introduce ZENO language construct to maintain high-level semantics and the type information (e.g., privacy and tensor) for allowing more aggressive optimizations. We then propose privacy-type driven and tensor-type driven optimizations to further optimize the generated zkSNARK circuit. Finally, we design a set of NN-centric system optimizations to further accelerate zkSNARK NNs. Experimental results show that ZENO achieves up to 8.5× end-to-end speedup than state-of-the-art zkSNARK NNs. We reduce proof time for VGG16 from 6 minutes to 48 seconds, which makes zkSNARK NNs practical.
@inproceedings{FengWWYD24,
title = {ZENO: A Type-based Optimization Framework for Zero Knowledge Neural Network Inference},
author = {Boyuan Feng and Zheng Wang and Yuke Wang and Shu Yang and Yufei Ding},
booktitle = {ASPLOS},
year = {2024},
doi = {10.1145/3617232.3624852}
}