SinaShield
Executive
SIEM
Pipeline
Routing
Noise
AI Analytics
Enrichment
Trace
Compliance
3
πΊπΈ EN
π«π· FR
πΈπ¦ AR
AS
Artificial Intelligence & ML
Predictive ML models & Triple Vote AI Engine
Cached Data
Updated: 1:52:35 PM
High
ML Accuracy
88.0%
Average prediction accuracy
Optimal
F1 Score
84.1%
Precision & recall balance
Excellent
Recall
88.6%
Relevant event detection
Stable
Model Drift (30 days)
8.0%
No retraining needed
Fast
Inference Time
9 ms
Per prediction
Active
Triple Vote AI Confidence
85%
3 model agreement
ML Model Performance (12 months)
M-12
M-11
M-10
M-9
M-8
M-7
M-6
M-5
M-4
M-3
M-2
M-1
80%
Accuracy range: 82% - 89%
90%
Accuracy Predictions
88.0%
Correct
Correct predictions
88.0%
Incorrect predictions
12.0%
Anomaly Detection (30 days)
Day 1
Avg: 11 anomalies/day
Day 30
Active Model Distribution
SecurityBERT
42%
ThreatClassifier
38%
CostOptimizer
20%
Triple Vote consensus uses all 3 models
Recent ML Predictions
Event ID
Type
Prediction
Confidence
Model
Action
evt-001
network_anomaly
threat
94.2%
SecurityBERT
View Raw
evt-002
auth_failure
suspicious
87.8%
ThreatClassifier
View Raw
evt-003
file_access
benign
91.5%
CostOptimizer
View Raw