Table 11 Performance comparison of trust evaluation techniques.

From: Design of a dynamic trust management and defense decision system for shared vehicle data based on blockchain and deep reinforcement learning

Model

Accuracy

Malicious detection latency (ms)

Training time (minutes)

Bayesian Model (Proposed)

93.8%

12.5

8.2

Fuzzy Logic

81.2%

9.8

0 (No Training Required)

Random Forest

88.7%

18.3

23.6

SVM

85.4%

16.7

15.9

Back to article page