GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs
Authors:
Open Access
- 27 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 155-162
Abstract
No abstract availableAll Related Versions
Funding Information
- MICIU/AEI/10.13039/501100011033 (CNS2023-144241)
- European Union NextGenerationEU/PRTR (CNS2023-144241)
- MICIU/AEI/10.13039/501100011033 (RYC2021-031966-I)
- European Union NextGenerationEU/PRTR (RYC2021-031966-I)
This publication has 13 references indexed in Scilit:
- Efficient Privacy-Preserving Recommendation on Sparse Data using Fully Homomorphic Encryption2025
- Hardware efficient arithmetic reconfigurable fully homomorphic encryption (ARFHE) accelerator of low power IoT based RISC-V processorAnalog Integrated Circuits and Signal Processing, 2025
- Flexagon: A Multi-dataflow Sparse-Sparse Matrix Multiplication Accelerator for Efficient DNN Processing2023
- On Architecting Fully Homomorphic Encryption-based Computing Systems2023
- OpenFHE2022
- VCSR: An Efficient GPU Memory-Aware Sparse FormatIEEE Transactions on Parallel and Distributed Systems, 2022
- Bootstrapping for HElib2015
- New Algorithms for Secure Outsourcing of Large-Scale Systems of Linear EquationsIEEE Transactions on Information Forensics and Security, 2014
- (Leveled) Fully Homomorphic Encryption without BootstrappingACM Transactions on Computation Theory, 2014
- Computing arbitrary functions of encrypted dataCommunications of the ACM, 2010