Paper 2023/162

AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE

Wei Ao, Michigan State University
Vishnu Naresh Boddeti, Michigan State University
Abstract

Secure inference of deep convolutional neural networks (CNNs) under RNS-CKKS involves polynomial approximation of unsupported non-linear activation functions. However, existing approaches have three main limitations: 1) Inflexibility: The polynomial approximation and associated homomorphic evaluation architecture are customized manually for each CNN architecture and do not generalize to other networks. 2) Suboptimal Approximation: Each activation function is approximated instead of the function represented by the CNN. 3) Restricted Design: Either high-degree or low-degree polynomial approximations are used. The former retains high accuracy but slows down inference due to bootstrapping operations, while the latter accelerates ciphertext inference but compromises accuracy. To address these limitations, we present AutoFHE, which automatically adapts standard CNNs for secure inference under RNS-CKKS. The key idea is to adopt layerwise mixed-degree polynomial activation functions, which are optimized jointly with the homomorphic evaluation architecture in terms of the placement of bootstrapping operations. The problem is modeled within a multi-objective optimization framework to maximize accuracy and minimize the number of bootstrapping operations. AutoFHE can be applied flexibly on any CNN architecture, and it provides diverse solutions that span the trade-off between accuracy and latency. Experimental evaluation over RNS-CKKS encrypted CIFAR datasets shows that AutoFHE accelerates secure inference by $1.32\times$ to $1.8\times$ compared to methods employing high-degree polynomials. It also improves accuracy by up to 2.56% compared to methods using low-degree polynomials. Lastly, AutoFHE accelerates inference and improves accuracy by $103\times$ and 3.46%, respectively, compared to CNNs under TFHE.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Published elsewhere. USENIX Security Symposium 2024
Keywords
Fully Homomorphic EncryptionDeep LearningAutomated Machine LearningSecure Inference
Contact author(s)
aowei @ msu edu
vishnu @ msu edu
History
2023-10-11: revised
2023-02-09: received
See all versions
Short URL
https://ia.cr/2023/162
License
Creative Commons Attribution-NonCommercial-ShareAlike
CC BY-NC-SA

BibTeX

@misc{cryptoeprint:2023/162,
      author = {Wei Ao and Vishnu Naresh Boddeti},
      title = {{AutoFHE}: Automated Adaption of {CNNs} for Efficient Evaluation over {FHE}},
      howpublished = {Cryptology {ePrint} Archive, Paper 2023/162},
      year = {2023},
      url = {https://eprint.iacr.org/2023/162}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.