Create app.py

app.py

@@ -0,0 +1,214 @@
+import dash
+from dash import dcc, html
+from dash.dependencies import Input, Output
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta
+from sklearn.ensemble import IsolationForest
+from sklearn.preprocessing import StandardScaler
+import plotly.graph_objs as go
+from plotly.subplots import make_subplots
+import warnings
+warnings.filterwarnings('ignore')
+
+class CyberSecurityAnalytics:
+    def __init__(self):
+        self.generate_data()
+        self.detect_anomalies()
+        
+    def generate_data(self, n_samples=100):
+        current_time = datetime.now()
+        timestamps = [current_time - timedelta(minutes=i) for i in range(n_samples)]
+        
+        self.data = pd.DataFrame({
+            'timestamp': timestamps,
+            'network_traffic': np.random.normal(1000, 200, n_samples),
+            'failed_logins': np.random.poisson(5, n_samples),
+            'suspicious_ips': np.random.poisson(2, n_samples),
+            'data_exfiltration': np.random.normal(50, 10, n_samples),
+            'severity': np.random.choice(['Low', 'Medium', 'High'], n_samples),
+            'source_country': np.random.choice(['USA', 'China', 'Russia', 'UK', 'India'], n_samples),
+            'attack_type': np.random.choice(['DDoS', 'Brute Force', 'SQL Injection', 'XSS', 'Malware'], n_samples),
+            'port': np.random.choice([80, 443, 22, 3389, 8080], n_samples)
+        })
+        
+    def detect_anomalies(self):
+        isolation_forest = IsolationForest(contamination=0.1, random_state=42)
+        scaler = StandardScaler()
+        
+        features = ['network_traffic', 'failed_logins', 'suspicious_ips', 'data_exfiltration']
+        X = self.data[features]
+        X_scaled = scaler.fit_transform(X)
+        
+        self.data['is_anomaly'] = isolation_forest.fit_predict(X_scaled) == -1
+
+    def plot_network_traffic(self):
+        fig = go.Figure()
+        
+        fig.add_trace(go.Scatter(
+            x=self.data[~self.data['is_anomaly']]['timestamp'],
+            y=self.data[~self.data['is_anomaly']]['network_traffic'],
+            name='Normal Traffic',
+            mode='lines',
+            line=dict(color='blue')
+        ))
+        
+        fig.add_trace(go.Scatter(
+            x=self.data[self.data['is_anomaly']]['timestamp'],
+            y=self.data[self.data['is_anomaly']]['network_traffic'],
+            name='Anomalies',
+            mode='markers',
+            marker=dict(color='red', size=10)
+        ))
+        
+        fig.update_layout(
+            title='Network Traffic with Anomaly Detection',
+            xaxis_title='Time',
+            yaxis_title='Network Traffic (bytes)',
+            template='plotly_white'
+        )
+        return fig
+    
+    def plot_security_overview(self):
+        fig = make_subplots(
+            rows=3, cols=2,
+            subplot_titles=('Network Traffic', 'Failed Login Attempts',
+                          'Attack Types', 'Geographic Distribution',
+                          'Port Activity', 'Severity Distribution'),
+            specs=[[{'type': 'scatter'}, {'type': 'bar'}],
+                  [{'type': 'pie'}, {'type': 'pie'}],
+                  [{'type': 'bar'}, {'type': 'bar'}]]
+        )
+        
+        fig.add_trace(
+            go.Scatter(x=self.data['timestamp'], y=self.data['network_traffic'],
+                      name='Network Traffic'),
+            row=1, col=1
+        )
+        
+        fig.add_trace(
+            go.Bar(x=self.data['timestamp'], y=self.data['failed_logins'],
+                  name='Failed Logins'),
+            row=1, col=2
+        )
+        
+        attack_counts = self.data['attack_type'].value_counts()
+        fig.add_trace(
+            go.Pie(labels=attack_counts.index, values=attack_counts.values,
+                  name='Attack Types'),
+            row=2, col=1
+        )
+        
+        country_counts = self.data['source_country'].value_counts()
+        fig.add_trace(
+            go.Pie(labels=country_counts.index, values=country_counts.values,
+                  name='Countries'),
+            row=2, col=2
+        )
+        
+        port_counts = self.data['port'].value_counts()
+        fig.add_trace(
+            go.Bar(x=port_counts.index, y=port_counts.values,
+                  name='Port Activity'),
+            row=3, col=1
+        )
+        
+        severity_counts = self.data['severity'].value_counts()
+        fig.add_trace(
+            go.Bar(x=severity_counts.index, y=severity_counts.values,
+                  name='Severity',
+                  marker_color=['green', 'yellow', 'red']),
+            row=3, col=2
+        )
+        
+        fig.update_layout(height=1200, showlegend=False,
+                         title_text="Security Overview Dashboard")
+        return fig
+
+    def generate_metrics_table(self):
+        metrics = {
+            'Total Anomalies': int(self.data['is_anomaly'].sum()),
+            'High Severity Alerts': int(len(self.data[self.data['severity'] == 'High'])),
+            'Average Network Traffic': f"{float(self.data['network_traffic'].mean()):.2f}",
+            'Max Failed Logins': int(self.data['failed_logins'].max()),
+            'Unique Attack Sources': int(self.data['source_country'].nunique()),
+            'Most Common Attack': str(self.data['attack_type'].mode()[0]),
+            'Most Targeted Port': int(self.data['port'].mode()[0])
+        }
+        
+        return html.Table(
+            [html.Tr([html.Th(key), html.Td(value)]) for key, value in metrics.items()],
+            className='metrics-table'
+        )
+
+# Initialize the Dash app
+app = dash.Dash(__name__)
+server = app.server
+
+# Initialize analytics
+security_analytics = CyberSecurityAnalytics()
+
+# Define the layout
+app.layout = html.Div([
+    html.H1("AI-Enhanced Cybersecurity Dashboard", 
+            style={'textAlign': 'center', 'padding': '20px'}),
+    
+    html.Div([
+        html.H2("Key Metrics", style={'textAlign': 'center'}),
+        security_analytics.generate_metrics_table()
+    ], style={'padding': '20px'}),
+    
+    html.Div([
+        html.H2("Network Traffic Analysis", style={'textAlign': 'center'}),
+        dcc.Graph(figure=security_analytics.plot_network_traffic())
+    ], style={'padding': '20px'}),
+    
+    html.Div([
+        html.H2("Security Overview", style={'textAlign': 'center'}),
+        dcc.Graph(figure=security_analytics.plot_security_overview())
+    ], style={'padding': '20px'})
+])
+
+# Add some CSS styling
+app.index_string = '''
+<!DOCTYPE html>
+<html>
+    <head>
+        {%metas%}
+        <title>Cybersecurity Dashboard</title>
+        {%favicon%}
+        {%css%}
+        <style>
+            body {
+                font-family: Arial, sans-serif;
+                margin: 0;
+                background-color: #f0f2f5;
+            }
+            .metrics-table {
+                width: 100%;
+                border-collapse: collapse;
+                margin: 20px 0;
+            }
+            .metrics-table th, .metrics-table td {
+                padding: 12px;
+                text-align: left;
+                border-bottom: 1px solid #ddd;
+            }
+            .metrics-table th {
+                background-color: #f8f9fa;
+            }
+        </style>
+    </head>
+    <body>
+        {%app_entry%}
+        <footer>
+            {%config%}
+            {%scripts%}
+            {%renderer%}
+        </footer>
+    </body>
+</html>
+'''
+
+if __name__ == '__main__':
+    app.run_server(debug=True)