Table 9 Comparative performance of DP-RBFN vs. DP-MLP models (\(\varepsilon = 0.5\)).

From: A service-oriented microservice framework for differential privacy-based protection in industrial IoT smart applications

Model

Accuracy (%)

Std. dev

Latency (ms)

Throughput

Accuracy loss

DP-RBFN

93.21

±1.12

58.3

17.1

2.8%

DP-MLP

91.87

±1.34

82.5

11.3

4.1%

Back to article page