skip to main content
10.1145/3649329.3656517acmconferencesArticle/Chapter ViewAbstractPublication PagesdacConference Proceedingsconference-collections
research-article

PPGNN: Fast and Accurate Privacy-Preserving Graph Neural Network Inference via Parallel and Pipelined Arithmetic-and-Logic FHE Accelerator

Published: 07 November 2024 Publication History

Abstract

Graph Neural Networks (GNNs) are increasingly used in fields like social media and bioinformatics, promoting the prosperity of cloud-based GNN inference services. Nevertheless, data privacy becomes a critical issue when handling sensitive information. Fully Homomorphic Encryption (FHE) enables computations on encrypted data, while privacy-preserving GNN inference generally necessitates ensuring graph structure data confidentiality and maintaining computation precision, both of which are computationally expensive in FHE. Existing schemes of GNNs inference with FHE are deterred by either computational overhead, accuracy degradation, or incomplete data protection. This paper presents PPGNN to address these challenges all at once. We first propose a novel privacy-preserving GNN inference algorithm utilizing a high-accuracy arithmetic-and-logic FHE approach, meanwhile only need much smaller parameters, substantially reducing computational complexity and facilitating parallel processing. Correspondingly, a dedicated hardware architecture has been designed to implement these innovations, with featured specialized units for arithmetic and logic FHE operations in a pipelined manner. Collectively, PPGNN achieves 2.7× and 1.5× speedup over state-of-the-art Arithmetic FHE and Logic FHE accelerators while ensuring high accuracy, simultaneously with about 18× energy reduction on average.

References

[1]
X. Wei et al., "Dual subgraph-based graph neural network for friendship prediction in location-based social networks," ACM Trans. Knowl. Discov. Data, vol. 17, no. 3, pp. 1--28, 2023.
[2]
H.-C. Yi et al., "Graph representation learning in bioinformatics: trends, methods and applications," Brief. Bioinform., vol. 23, no. 1, p. bbab340, 2022.
[3]
S. Wu et al., "Graph neural networks in recommender systems: a survey," ACM Comput. Surv., vol. 55, no. 5, pp. 1--37, 2022.
[4]
I. Baidu, "Paddlehelix," 2023.
[5]
J. Wang et al., "A review on graph neural network methods in financial applications," arXiv, 2021.
[6]
R. Gilad-Bachrach et al., "Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy," in ICML 2016. PMLR, 2016, pp. 201--210.
[7]
Q. Lou et al., "Autoprivacy: Automated layer-wise parameter selection for secure neural network inference," NeurIPS, vol. 33, pp. 8638--8647, 2020.
[8]
S. Bian et al., "Ensei: Efficient secure inference via frequency-domain homomorphic convolution for privacy-preserving visual recognition," in CVPR 2020, 2020, pp. 9403--9412.
[9]
Z. Huang et al., "Cheetah: Lean and fast secure two-party deep neural network inference." in USENIX Security 2022, 2022, pp. 2505--2522.
[10]
Y. Wei et al., "THE-V: Verifiable privacy-preserving neural network via trusted homomorphic execution," in ICCAD 2023. IEEE, 2023, pp. 1--9.
[11]
R. Ran et al., "CryptoGCN: Fast and scalable homomorphically encrypted graph convolutional network inference," NeurIPS, vol. 35, pp. 37 676--37 689, 2022.
[12]
J. H. Cheon et al., "Homomorphic encryption for arithmetic of approximate numbers," in ASIACRYPT 2017. Springer, 2017, pp. 409--437.
[13]
I. Chillotti et al., "TFHE: fast fully homomorphic encryption over the torus," J. Cryptology, vol. 33, no. 1, pp. 34--91, 2020.
[14]
S. Lee et al., "HETAL: Efficient privacy-preserving transfer learning with homomorphic encryption," in ICML 2023. PMLR, 2023, pp. 19 010--19 035.
[15]
N. Samardzic et al., "F1: A fast and programmable accelerator for fully homomorphic encryption," in MICRO 2021, 2021, pp. 238--252.
[16]
N. Samardzic et al., "Craterlake: a hardware accelerator for efficient unbounded computation on encrypted data," in ISCA 2022, 2022, pp. 173--187.
[17]
Zama, "TFHE-rs: A Pure Rust Implementation of the TFHE Scheme for Boolean and Integer Arithmetics Over Encrypted Data," 2022, https://github.com/zamaai/tfhe-rs.
[18]
A. Putra et al., "Strix: An end-to-end streaming architecture with two-level ciphertext batching for fully homomorphic encryption with programmable bootstrapping," MICRO 2023, 2023.
[19]
Y. Wei et al., "IMGA: Efficient in-memory graph convolution network aggregation with data flow optimizations," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023.
[20]
I. Chillotti et al., "Programmable bootstrapping enables efficient homomorphic inference of deep neural networks," in CSML 2021. Springer, 2021, pp. 1--19.
[21]
J. Kim et al., "SHARP: A short-word hierarchical accelerator for robust and practical fully homomorphic encryption," in ISCA 2023, 2023, pp. 1--15.
[22]
C. Gentry et al., "Homomorphic evaluation of the aes circuit," in CRYPTO 2012. Springer, 2012, pp. 850--867.
[23]
K. Nam et al., "Accelerating n-bit operations over tfhe on commodity cpu-fpga," in ICCAD 2022, 2022, pp. 1--9.
[24]
H. Chen et al., "Efficient homomorphic conversion between (ring) lwe ciphertexts," in ACNS 2021. Springer, 2021, pp. 460--479.
[25]
T. Yang et al., "PIMGCN: a reram-based pim design for graph convolutional network acceleration," in DAC 2021. IEEE, 2021, pp. 583--588.
[26]
S. Wang et al., "SecGNN: Privacy-preserving graph neural network training and inference as a cloud service," IEEE Trans. Serv. Comput., 2023.
[27]
O. Villa et al., "Scaling the power wall: a path to exascale," in SC 2014. IEEE, 2014, pp. 830--841.
[28]
"Microsoft SEAL (release 4.1)," https://github.com/Microsoft/SEAL, Jan. 2023, microsoft Research, Redmond, WA.
[29]
C. Juvekar et al., "GAZELLE: A low latency framework for secure neural network inference," in USENIX Security 2018), 2018, pp. 1651--1669.
[30]
L. Jiang et al., "MATCHA: A fast and energy-efficient accelerator for fully homomorphic encryption over the torus," in DAC 2022, 2022, pp. 235--240.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
DAC '24: Proceedings of the 61st ACM/IEEE Design Automation Conference
June 2024
2159 pages
ISBN:9798400706011
DOI:10.1145/3649329
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

In-Cooperation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 November 2024

Check for updates

Author Tags

  1. graph neural networks
  2. privacy-preserving
  3. fully homomorphic encryption
  4. hardware-software co-design

Qualifiers

  • Research-article

Funding Sources

Conference

DAC '24
Sponsor:
DAC '24: 61st ACM/IEEE Design Automation Conference
June 23 - 27, 2024
CA, San Francisco, USA

Acceptance Rates

Overall Acceptance Rate 1,770 of 5,499 submissions, 32%

Upcoming Conference

DAC '25
62nd ACM/IEEE Design Automation Conference
June 22 - 26, 2025
San Francisco , CA , USA

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 141
    Total Downloads
  • Downloads (Last 12 months)141
  • Downloads (Last 6 weeks)42
Reflects downloads up to 25 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media