A triple-hoisted BSGS algorithm for CKKS linear transforms plus FPGA accelerator reduces off-chip memory access 2.9x and computational latency 5.8x versus prior best designs.
Better bootstrapping for approxi- mate homomorphic encryption
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Triple-Hoisted Baby-Step Giant-Step Linear Transformation over CKKS Homomorphic Encryption and Hardware Accelerator
A triple-hoisted BSGS algorithm for CKKS linear transforms plus FPGA accelerator reduces off-chip memory access 2.9x and computational latency 5.8x versus prior best designs.