Table 9 Practical impact of improved trust evaluation accuracy.

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

Metric

Traditional model

BTB-MDQN model

Improvement percentage

Misjudgment Rate

12.4%

1.9%

84.7%

User Complaint Rate (per 10,000 requests)

0.45

0.28

37.8%

Malicious Attack Interception Rate

78%

93.8%

20.3%

Back to article page