WHET applies fine-grained coefficient-to-slot transforms, plaintext compression, and modulus raising plus lightweight hardware tweaks to FHE accelerators, delivering 1.38-8.74x per-area gains and sub-millisecond CKKS bootstrapping.
InSelected Areas in Cryptography
2 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ComputeFHE supplies TFHE encrypted data types and operations with an optimized ALU that reduces bootstrapping operations, yielding up to 3.9x speedup on selected tasks plus a simulation mode for complexity analysis.
citing papers explorer
-
WHET: Welding Homomorphic Encryption to Accelerator Architectures
WHET applies fine-grained coefficient-to-slot transforms, plaintext compression, and modulus raising plus lightweight hardware tweaks to FHE accelerators, delivering 1.38-8.74x per-area gains and sub-millisecond CKKS bootstrapping.
-
ComputeFHE: A Privacy-Preserving General-Purpose Computation Library
ComputeFHE supplies TFHE encrypted data types and operations with an optimized ALU that reduces bootstrapping operations, yielding up to 3.9x speedup on selected tasks plus a simulation mode for complexity analysis.