PYthon For Homomorphic Encryption Libraries, perform encrypted computations such as sum, mult, scalar product or matrix multiplication in Python, with NumPy compatibility. Uses SEAL/PALISADE as backends, implemented using Cython.
I’m trying to compare CKKS scheme between Pyfhel and TenSeal in Python. The experiment settings are:
128 security level
Polynomial degree (N) = 8192
First Mod Size (Q0) = 60
Scaling Mod Size = 49
Multiplicative depth = 2
Two float arrays, each has 1000 elements. One constant
The following execution time are measured:
Enc: encode + encrypt
AddCC: add two ciphertext
MultCC: multiply two ciphertext
MultCConst: multiply one ciphertext and a constant
DecAddCC: decrypt AddCC
DecMultCC: decrypt MultCC
DecMultCConst: decrypt MultCConst
Each operation is executed 500 times and taken average with 12th Gen Intel® Core™ i7-12700KF CPU.
Based on the result, time taken for Pyfhel is longer than TenSeal, especially for decryption.
May I ask what may be the potential cause that makes Pyfhel takes more time compared to TenSeal?
Hi,
I’m trying to compare CKKS scheme between Pyfhel and TenSeal in Python. The experiment settings are:
128 security level Polynomial degree (N) = 8192 First Mod Size (Q0) = 60 Scaling Mod Size = 49 Multiplicative depth = 2 Two float arrays, each has 1000 elements. One constant The following execution time are measured:
Enc: encode + encrypt AddCC: add two ciphertext MultCC: multiply two ciphertext MultCConst: multiply one ciphertext and a constant DecAddCC: decrypt AddCC DecMultCC: decrypt MultCC DecMultCConst: decrypt MultCConst Each operation is executed 500 times and taken average with 12th Gen Intel® Core™ i7-12700KF CPU.
Based on the result, time taken for Pyfhel is longer than TenSeal, especially for decryption.
May I ask what may be the potential cause that makes Pyfhel takes more time compared to TenSeal?
Thank you