Table 8 Differential privacy configuration for Health-FedNet.

From: Health-FedNet: secure federated learning for chronic disease prediction on MIMIC-III with differential privacy and homomorphic encryption

Parameter

Symbol

Value

Clipping Norm

C

1.2

Noise Standard Deviation

σ

0.8

Privacy Budget (per round)

Failure Probability

εr

Ī“

0.15

10ā€‰āˆ’ā€‰5

Sampling Rate

q

0.05

Total Training Rounds

R

20

Accountant Method

–

RDP + Moments Accountant

Final Privacy Guarantee

(ε, Γ )

(1.53, 10āˆ’5)