Benchmarking finds FHE faster than SMPC for regressions and simple dense networks (especially with GPUs), while SMPC performs better on complex CNN models.
Faster Bootstrapping With Multiple Addends , year=
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
-
A Pragmatic Comparison of Cryptographic Computation Technologies for Machine Learning
Benchmarking finds FHE faster than SMPC for regressions and simple dense networks (especially with GPUs), while SMPC performs better on complex CNN models.