Paper 2025/1534
RBOOT: Accelerating Homomorphic Neural Network Inference by Fusing ReLU within Bootstrapping
Abstract
A major bottleneck in secure neural network inference using Fully Homomorphic Encryption (FHE) is the evaluation of non-linear activation functions like ReLU, which are inefficient to compute under FHE. State-of-the-art solutions approximate ReLU using high-degree polynomials, incurring significant computational overhead. We propose novel methods for functional bootstrapping with CKKS, and based on these methods we present RBOOT, an optimized framework that seamlessly integrates ReLU evaluation into CKKS bootstrapping, significantly reducing multiplication depth and boosting efficiency. Our key insight is that the EvalMod step in CKKS bootstrapping is composed of trigonometric functions, which can be transformed into various common non-linear functions. By co-optimizing these components, we can exploit such non-linearity to construct ReLU (and other non-linear functions) within the bootstrapping process itself, greatly reducing the computation overhead. Results on four widely used CNN models show that RBOOT achieves $2.77\times$ faster end-to-end inference and $81\%$ lower memory usage compared to previous polynomial approximation works, while maintaining comparable accuracy.
Metadata
- Available format(s)
-
PDF
- Category
- Applications
- Publication info
- Preprint.
- Keywords
- fully homomorphic encryptionCKKSfunctional bootstrappingprivacy-preserving
- Contact author(s)
-
yangzhaomin yzm @ antgroup com
niuchao niu @ antgroup com
weibenqiang wbq @ antgroup com
zhicong hzc @ antgroup com
vince hc @ antgroup com
lenx wei @ antgroup com - History
- 2025-08-30: approved
- 2025-08-27: received
- See all versions
- Short URL
- https://ia.cr/2025/1534
- License
-
CC BY-NC
BibTeX
@misc{cryptoeprint:2025/1534,
author = {Zhaomin Yang and Chao Niu and Benqiang Wei and Zhicong Huang and Cheng Hong and Tao Wei},
title = {{RBOOT}: Accelerating Homomorphic Neural Network Inference by Fusing {ReLU} within Bootstrapping},
howpublished = {Cryptology {ePrint} Archive, Paper 2025/1534},
year = {2025},
url = {https://eprint.iacr.org/2025/1534}
}