Phishing Simulations

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588

import pandas as pd
import numpy as np
from datetime import datetime, timedelta
import json
import random

class PhishingSimulationSystem:
    def __init__(self):
        self.simulations = {}
        self.templates = {}
        self.campaigns = {}
        self.results = {}
        self.behavior_analysis = {}
        self.improvement_recommendations = {}
    
    def create_phishing_template(self, template_id, template_config):
        """Create phishing simulation template"""
        self.templates[template_id] = {
            'template_id': template_id,
            'name': template_config['name'],
            'category': template_config['category'],
            'difficulty_level': template_config['difficulty_level'],
            'subject_line': template_config['subject_line'],
            'sender_name': template_config['sender_name'],
            'sender_email': template_config['sender_email'],
            'email_content': template_config['email_content'],
            'phishing_indicators': template_config.get('phishing_indicators', []),
            'social_engineering_tactics': template_config.get('social_engineering_tactics', []),
            'target_audience': template_config.get('target_audience', 'all'),
            'success_criteria': template_config.get('success_criteria', {}),
            'created_date': datetime.now(),
            'version': 1.0
        }
    
    def create_simulation_campaign(self, campaign_id, campaign_config):
        """Create simulation campaign"""
        self.campaigns[campaign_id] = {
            'campaign_id': campaign_id,
            'name': campaign_config['name'],
            'description': campaign_config['description'],
            'template_id': campaign_config['template_id'],
            'target_audience': campaign_config['target_audience'],
            'scheduling': campaign_config['scheduling'],
            'delivery_method': campaign_config.get('delivery_method', 'email'),
            'randomization': campaign_config.get('randomization', True),
            'follow_up_training': campaign_config.get('follow_up_training', True),
            'status': 'scheduled',
            'created_date': datetime.now(),
            'start_date': campaign_config.get('start_date'),
            'end_date': campaign_config.get('end_date'),
            'total_recipients': 0,
            'emails_sent': 0,
            'emails_delivered': 0,
            'emails_opened': 0,
            'links_clicked': 0,
            'attachments_opened': 0,
            'data_entered': 0,
            'reported_phishing': 0,
            'false_positives': 0
        }
    
    def execute_simulation(self, campaign_id, recipient_list):
        """Execute phishing simulation"""
        if campaign_id not in self.campaigns:
            return False
        
        campaign = self.campaigns[campaign_id]
        template = self.templates[campaign['template_id']]
        
        campaign['status'] = 'running'
        campaign['total_recipients'] = len(recipient_list)
        
        for recipient in recipient_list:
            simulation_id = f"SIM-{len(self.simulations) + 1}"
            
            # Create individual simulation
            simulation = {
                'simulation_id': simulation_id,
                'campaign_id': campaign_id,
                'template_id': campaign['template_id'],
                'recipient_id': recipient['recipient_id'],
                'recipient_email': recipient['email'],
                'recipient_name': recipient['name'],
                'department': recipient.get('department', 'unknown'),
                'role': recipient.get('role', 'employee'),
                'risk_level': recipient.get('risk_level', 'medium'),
                'sent_date': datetime.now(),
                'delivered': False,
                'delivered_date': None,
                'opened': False,
                'opened_date': None,
                'link_clicked': False,
                'link_clicked_date': None,
                'attachment_opened': False,
                'attachment_opened_date': None,
                'data_entered': False,
                'data_entered_date': None,
                'reported_phishing': False,
                'reported_date': None,
                'response_time_minutes': None,
                'vulnerability_score': 0,
                'training_assigned': False
            }
            
            self.simulations[simulation_id] = simulation
            
            # Simulate delivery
            if self.simulate_delivery():
                simulation['delivered'] = True
                simulation['delivered_date'] = datetime.now()
                campaign['emails_delivered'] += 1
            
            campaign['emails_sent'] += 1
        
        return True
    
    def simulate_delivery(self):
        """Simulate email delivery"""
        # Simulate 95% delivery rate
        return random.random() < 0.95
    
    def record_email_opened(self, simulation_id):
        """Record email opening"""
        if simulation_id not in self.simulations:
            return False
        
        simulation = self.simulations[simulation_id]
        
        if not simulation['opened']:
            simulation['opened'] = True
            simulation['opened_date'] = datetime.now()
            
            # Calculate response time
            if simulation['delivered_date']:
                response_time = simulation['opened_date'] - simulation['delivered_date']
                simulation['response_time_minutes'] = response_time.total_seconds() / 60
            
            # Update campaign statistics
            campaign_id = simulation['campaign_id']
            if campaign_id in self.campaigns:
                self.campaigns[campaign_id]['emails_opened'] += 1
            
            # Calculate vulnerability score
            self.calculate_vulnerability_score(simulation_id)
        
        return True
    
    def record_link_clicked(self, simulation_id):
        """Record link click"""
        if simulation_id not in self.simulations:
            return False
        
        simulation = self.simulations[simulation_id]
        
        if not simulation['link_clicked']:
            simulation['link_clicked'] = True
            simulation['link_clicked_date'] = datetime.now()
            
            # Update campaign statistics
            campaign_id = simulation['campaign_id']
            if campaign_id in self.campaigns:
                self.campaigns[campaign_id]['links_clicked'] += 1
            
            # Recalculate vulnerability score
            self.calculate_vulnerability_score(simulation_id)
        
        return True
    
    def record_attachment_opened(self, simulation_id):
        """Record attachment opening"""
        if simulation_id not in self.simulations:
            return False
        
        simulation = self.simulations[simulation_id]
        
        if not simulation['attachment_opened']:
            simulation['attachment_opened'] = True
            simulation['attachment_opened_date'] = datetime.now()
            
            # Update campaign statistics
            campaign_id = simulation['campaign_id']
            if campaign_id in self.campaigns:
                self.campaigns[campaign_id]['attachments_opened'] += 1
            
            # Recalculate vulnerability score
            self.calculate_vulnerability_score(simulation_id)
        
        return True
    
    def record_data_entered(self, simulation_id):
        """Record data entry"""
        if simulation_id not in self.simulations:
            return False
        
        simulation = self.simulations[simulation_id]
        
        if not simulation['data_entered']:
            simulation['data_entered'] = True
            simulation['data_entered_date'] = datetime.now()
            
            # Update campaign statistics
            campaign_id = simulation['campaign_id']
            if campaign_id in self.campaigns:
                self.campaigns[campaign_id]['data_entered'] += 1
            
            # Recalculate vulnerability score
            self.calculate_vulnerability_score(simulation_id)
        
        return True
    
    def record_phishing_report(self, simulation_id):
        """Record phishing report"""
        if simulation_id not in self.simulations:
            return False
        
        simulation = self.simulations[simulation_id]
        
        if not simulation['reported_phishing']:
            simulation['reported_phishing'] = True
            simulation['reported_date'] = datetime.now()
            
            # Update campaign statistics
            campaign_id = simulation['campaign_id']
            if campaign_id in self.campaigns:
                self.campaigns[campaign_id]['reported_phishing'] += 1
            
            # Recalculate vulnerability score
            self.calculate_vulnerability_score(simulation_id)
        
        return True
    
    def calculate_vulnerability_score(self, simulation_id):
        """Calculate vulnerability score"""
        if simulation_id not in self.simulations:
            return 0
        
        simulation = self.simulations[simulation_id]
        
        score = 0
        
        # Points for risk actions
        if simulation['opened']:
            score += 10
        
        if simulation['link_clicked']:
            score += 30
        
        if simulation['attachment_opened']:
            score += 40
        
        if simulation['data_entered']:
            score += 50
        
        # Negative points for reporting
        if simulation['reported_phishing']:
            score -= 20
        
        # Adjust for response time
        if simulation['response_time_minutes'] is not None:
            if simulation['response_time_minutes'] < 5:  # Very fast response
                score += 10
            elif simulation['response_time_minutes'] > 60:  # Slow response
                score -= 5
        
        # Adjust for user risk level
        risk_level = simulation.get('risk_level', 'medium')
        if risk_level == 'high':
            score *= 1.2
        elif risk_level == 'low':
            score *= 0.8
        
        simulation['vulnerability_score'] = max(0, min(100, score))
        return simulation['vulnerability_score']
    
    def analyze_campaign_results(self, campaign_id):
        """Analyze campaign results"""
        if campaign_id not in self.campaigns:
            return None
        
        campaign = self.campaigns[campaign_id]
        campaign_simulations = [s for s in self.simulations.values() if s['campaign_id'] == campaign_id]
        
        if not campaign_simulations:
            return None
        
        # Basic metrics
        total_simulations = len(campaign_simulations)
        delivered_simulations = len([s for s in campaign_simulations if s['delivered']])
        opened_simulations = len([s for s in campaign_simulations if s['opened']])
        clicked_simulations = len([s for s in campaign_simulations if s['link_clicked']])
        data_entered_simulations = len([s for s in campaign_simulations if s['data_entered']])
        reported_simulations = len([s for s in campaign_simulations if s['reported_phishing']])
        
        # Calculate rates
        delivery_rate = (delivered_simulations / total_simulations * 100) if total_simulations > 0 else 0
        open_rate = (opened_simulations / delivered_simulations * 100) if delivered_simulations > 0 else 0
        click_rate = (clicked_simulations / total_simulations * 100) if total_simulations > 0 else 0
        data_entry_rate = (data_entered_simulations / total_simulations * 100) if total_simulations > 0 else 0
        report_rate = (reported_simulations / total_simulations * 100) if total_simulations > 0 else 0
        
        # Calculate average vulnerability score
        vulnerability_scores = [s['vulnerability_score'] for s in campaign_simulations]
        avg_vulnerability_score = sum(vulnerability_scores) / len(vulnerability_scores) if vulnerability_scores else 0
        
        # Analysis by department
        dept_analysis = {}
        for sim in campaign_simulations:
            dept = sim.get('department', 'unknown')
            if dept not in dept_analysis:
                dept_analysis[dept] = {
                    'total': 0,
                    'clicked': 0,
                    'reported': 0,
                    'vulnerability_scores': []
                }
            
            dept_analysis[dept]['total'] += 1
            if sim['link_clicked']:
                dept_analysis[dept]['clicked'] += 1
            if sim['reported_phishing']:
                dept_analysis[dept]['reported'] += 1
            
            dept_analysis[dept]['vulnerability_scores'].append(sim['vulnerability_score'])
        
        # Calculate metrics per department
        for dept, data in dept_analysis.items():
            data['click_rate'] = (data['clicked'] / data['total'] * 100) if data['total'] > 0 else 0
            data['report_rate'] = (data['reported'] / data['total'] * 100) if data['total'] > 0 else 0
            data['avg_vulnerability'] = sum(data['vulnerability_scores']) / len(data['vulnerability_scores']) if data['vulnerability_scores'] else 0
        
        # Temporal analysis
        hourly_analysis = {}
        for sim in campaign_simulations:
            if sim['opened_date']:
                hour = sim['opened_date'].hour
                if hour not in hourly_analysis:
                    hourly_analysis[hour] = {'opened': 0, 'clicked': 0, 'reported': 0}
                
                hourly_analysis[hour]['opened'] += 1
                if sim['link_clicked']:
                    hourly_analysis[hour]['clicked'] += 1
                if sim['reported_phishing']:
                    hourly_analysis[hour]['reported'] += 1
        
        # Determine risk level
        risk_level = self.determine_campaign_risk_level(avg_vulnerability_score, click_rate, data_entry_rate, report_rate)
        
        results = {
            'campaign_id': campaign_id,
            'total_simulations': total_simulations,
            'delivery_rate': delivery_rate,
            'open_rate': open_rate,
            'click_rate': click_rate,
            'data_entry_rate': data_entry_rate,
            'report_rate': report_rate,
            'avg_vulnerability_score': avg_vulnerability_score,
            'risk_level': risk_level,
            'department_analysis': dept_analysis,
            'hourly_analysis': hourly_analysis,
            'vulnerable_users': len([s for s in campaign_simulations if s['vulnerability_score'] > 70]),
            'high_risk_users': len([s for s in campaign_simulations if s['vulnerability_score'] > 90])
        }
        
        return results
    
    def determine_campaign_risk_level(self, avg_vulnerability, click_rate, data_entry_rate, report_rate):
        """Determine campaign risk level"""
        risk_score = 0
        
        # Risk factors
        if avg_vulnerability > 80:
            risk_score += 40
        elif avg_vulnerability > 60:
            risk_score += 30
        elif avg_vulnerability > 40:
            risk_score += 20
        
        if click_rate > 30:
            risk_score += 25
        elif click_rate > 20:
            risk_score += 15
        
        if data_entry_rate > 15:
            risk_score += 30
        elif data_entry_rate > 10:
            risk_score += 20
        
        if report_rate < 10:
            risk_score += 15
        elif report_rate < 20:
            risk_score += 10
        
        # Determine level
        if risk_score >= 80:
            return 'critical'
        elif risk_score >= 60:
            return 'high'
        elif risk_score >= 40:
            return 'medium'
        else:
            return 'low'
    
    def generate_improvement_recommendations(self, campaign_id):
        """Generate improvement recommendations"""
        results = self.analyze_campaign_results(campaign_id)
        if not results:
            return []
        
        recommendations = []
        
        # Recommendations based on general metrics
        if results['click_rate'] > 25:
            recommendations.append({
                'type': 'click_rate',
                'priority': 'high',
                'description': f"High click rate ({results['click_rate']:.1f}%) - implement additional phishing identification training",
                'action': 'Schedule additional phishing awareness training'
            })
        
        if results['data_entry_rate'] > 15:
            recommendations.append({
                'type': 'data_entry',
                'priority': 'critical',
                'description': f"High data entry rate ({results['data_entry_rate']:.1f}%) - critical compromise risk",
                'action': 'Implement immediate security awareness intervention'
            })
        
        if results['report_rate'] < 15:
            recommendations.append({
                'type': 'reporting',
                'priority': 'high',
                'description': f"Low reporting rate ({results['report_rate']:.1f}%) - improve reporting channels and incentives",
                'action': 'Improve reporting channels and create reporting incentives'
            })
        
        if results['avg_vulnerability_score'] > 70:
            recommendations.append({
                'type': 'vulnerability',
                'priority': 'high',
                'description': f"High vulnerability score ({results['avg_vulnerability_score']:.1f}) - review awareness program",
                'action': 'Review and enhance security awareness program'
            })
        
        # Recommendations based on department analysis
        for dept, data in results['department_analysis'].items():
            if data['click_rate'] > 40:
                recommendations.append({
                    'type': 'department_training',
                    'priority': 'medium',
                    'description': f"Specific training for {dept} - high click rate ({data['click_rate']:.1f}%)",
                    'action': f"Schedule department-specific training for {dept}"
                })
            
            if data['avg_vulnerability'] > 80:
                recommendations.append({
                    'type': 'department_intervention',
                    'priority': 'high',
                    'description': f"Immediate intervention for {dept} - critical vulnerability score ({data['avg_vulnerability']:.1f})",
                    'action': f"Implement immediate intervention for {dept}"
                })
        
        # Recommendations based on high-risk users
        if results['high_risk_users'] > 0:
            recommendations.append({
                'type': 'high_risk_users',
                'priority': 'critical',
                'description': f"{results['high_risk_users']} high-risk users identified - immediate attention required",
                'action': 'Schedule one-on-one security training for high-risk users'
            })
        
        return recommendations
    
    def generate_campaign_report(self, campaign_id):
        """Generate campaign report"""
        if campaign_id not in self.campaigns:
            return None
        
        campaign = self.campaigns[campaign_id]
        results = self.analyze_campaign_results(campaign_id)
        
        if not results:
            return None
        
        recommendations = self.generate_improvement_recommendations(campaign_id)
        
        report = {
            'campaign_id': campaign_id,
            'campaign_name': campaign['name'],
            'template_name': self.templates[campaign['template_id']]['name'],
            'report_date': datetime.now(),
            'executive_summary': {
                'total_participants': results['total_simulations'],
                'risk_level': results['risk_level'],
                'key_metrics': {
                    'click_rate': results['click_rate'],
                    'data_entry_rate': results['data_entry_rate'],
                    'report_rate': results['report_rate'],
                    'avg_vulnerability': results['avg_vulnerability_score']
                }
            },
            'detailed_results': results,
            'recommendations': recommendations,
            'next_steps': self.generate_next_steps(recommendations),
            'status': campaign['status']
        }
        
        return report
    
    def generate_next_steps(self, recommendations):
        """Generate next steps based on recommendations"""
        next_steps = []
        
        critical_recommendations = [r for r in recommendations if r['priority'] == 'critical']
        high_recommendations = [r for r in recommendations if r['priority'] == 'high']
        
        if critical_recommendations:
            next_steps.append({
                'timeline': 'Immediate',
                'actions': [r['action'] for r in critical_recommendations],
                'priority': 'Critical'
            })
        
        if high_recommendations:
            next_steps.append({
                'timeline': 'Within 1 week',
                'actions': [r['action'] for r in high_recommendations],
                'priority': 'High'
            })
        
        medium_recommendations = [r for r in recommendations if r['priority'] == 'medium']
        if medium_recommendations:
            next_steps.append({
                'timeline': 'Within 1 month',
                'actions': [r['action'] for r in medium_recommendations],
                'priority': 'Medium'
            })
        
        return next_steps

# Usage example
phishing_sim = PhishingSimulationSystem()

# Create phishing template
phishing_sim.create_phishing_template('TEMP-001', {
    'name': 'Banking Phishing Simulation',
    'category': 'financial',
    'difficulty_level': 'medium',
    'subject_line': 'Urgent: Verify Your Account Information',
    'sender_name': 'Security Team',
    'sender_email': 'security@bank.com',
    'email_content': 'Please click the link below to verify your account...',
    'phishing_indicators': ['urgent_language', 'suspicious_link', 'generic_greeting'],
    'social_engineering_tactics': ['urgency', 'authority', 'fear'],
    'target_audience': 'all_employees'
})

# Create simulation campaign
phishing_sim.create_simulation_campaign('CAMP-001', {
    'name': 'Q1 2025 Phishing Simulation',
    'description': 'Phishing simulation to evaluate awareness',
    'template_id': 'TEMP-001',
    'target_audience': 'all_employees',
    'scheduling': 'immediate',
    'delivery_method': 'email',
    'randomization': True,
    'follow_up_training': True
})

# Recipient list
recipients = [
    {'recipient_id': 'EMP-001', 'email': 'john.doe@company.com', 'name': 'John Doe', 'department': 'HR', 'role': 'manager'},
    {'recipient_id': 'EMP-002', 'email': 'jane.smith@company.com', 'name': 'Jane Smith', 'department': 'IT', 'role': 'engineer'},
    {'recipient_id': 'EMP-003', 'email': 'bob.wilson@company.com', 'name': 'Bob Wilson', 'department': 'Finance', 'role': 'analyst'}
]

# Execute simulation
phishing_sim.execute_simulation('CAMP-001', recipients)

# Simulate events
phishing_sim.record_email_opened('SIM-1')
phishing_sim.record_link_clicked('SIM-1')
phishing_sim.record_phishing_report('SIM-2')

# Generate report
report = phishing_sim.generate_campaign_report('CAMP-001')
print(f"Simulation report: {report['campaign_name']}")
print(f"Risk level: {report['executive_summary']['risk_level']}")
print(f"Click rate: {report['executive_summary']['key_metrics']['click_rate']:.1f}%")

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257

class BehaviorAnalysis:
    def __init__(self):
        self.behavior_patterns = {}
        self.risk_profiles = {}
        self.training_recommendations = {}
    
    def analyze_user_behavior(self, user_id, simulation_history):
        """Analyze specific user behavior"""
        if not simulation_history:
            return None
        
        # Calculate behavior metrics
        total_simulations = len(simulation_history)
        clicked_count = len([s for s in simulation_history if s['link_clicked']])
        reported_count = len([s for s in simulation_history if s['reported_phishing']])
        data_entered_count = len([s for s in simulation_history if s['data_entered']])
        
        # Calculate rates
        click_rate = (clicked_count / total_simulations * 100) if total_simulations > 0 else 0
        report_rate = (reported_count / total_simulations * 100) if total_simulations > 0 else 0
        data_entry_rate = (data_entered_count / total_simulations * 100) if total_simulations > 0 else 0
        
        # Calculate average vulnerability score
        vulnerability_scores = [s['vulnerability_score'] for s in simulation_history]
        avg_vulnerability = sum(vulnerability_scores) / len(vulnerability_scores) if vulnerability_scores else 0
        
        # Trend analysis
        trend_analysis = self.analyze_behavior_trends(simulation_history)
        
        # Create risk profile
        risk_profile = self.create_risk_profile(click_rate, report_rate, data_entry_rate, avg_vulnerability, trend_analysis)
        
        behavior_analysis = {
            'user_id': user_id,
            'total_simulations': total_simulations,
            'click_rate': click_rate,
            'report_rate': report_rate,
            'data_entry_rate': data_entry_rate,
            'avg_vulnerability': avg_vulnerability,
            'risk_profile': risk_profile,
            'trend_analysis': trend_analysis,
            'training_recommendations': self.generate_user_training_recommendations(risk_profile, trend_analysis)
        }
        
        return behavior_analysis
    
    def analyze_behavior_trends(self, simulation_history):
        """Analyze behavior trends"""
        if len(simulation_history) < 3:
            return {'trend': 'insufficient_data'}
        
        # Sort by date
        sorted_simulations = sorted(simulation_history, key=lambda x: x['sent_date'])
        
        # Analyze vulnerability trend
        vulnerability_trend = [s['vulnerability_score'] for s in sorted_simulations]
        
        # Calculate trend using linear regression
        x = np.arange(len(vulnerability_trend))
        y = np.array(vulnerability_trend)
        
        if len(x) > 1:
            slope = np.polyfit(x, y, 1)[0]
            if slope > 5:
                trend = 'increasing_risk'
            elif slope < -5:
                trend = 'decreasing_risk'
            else:
                trend = 'stable'
        else:
            trend = 'stable'
        
        # Analyze response patterns
        response_patterns = {
            'consistent_clicker': len([s for s in sorted_simulations if s['link_clicked']]) > len(sorted_simulations) * 0.7,
            'consistent_reporter': len([s for s in sorted_simulations if s['reported_phishing']]) > len(sorted_simulations) * 0.7,
            'improving': trend == 'decreasing_risk',
            'declining': trend == 'increasing_risk'
        }
        
        return {
            'vulnerability_trend': trend,
            'response_patterns': response_patterns,
            'data_points': len(sorted_simulations)
        }
    
    def create_risk_profile(self, click_rate, report_rate, data_entry_rate, avg_vulnerability, trend_analysis):
        """Create user risk profile"""
        risk_score = 0
        
        # Risk factors
        if click_rate > 50:
            risk_score += 30
        elif click_rate > 30:
            risk_score += 20
        elif click_rate > 15:
            risk_score += 10
        
        if data_entry_rate > 20:
            risk_score += 40
        elif data_entry_rate > 10:
            risk_score += 25
        elif data_entry_rate > 5:
            risk_score += 15
        
        if report_rate < 10:
            risk_score += 20
        elif report_rate < 25:
            risk_score += 10
        
        if avg_vulnerability > 80:
            risk_score += 30
        elif avg_vulnerability > 60:
            risk_score += 20
        elif avg_vulnerability > 40:
            risk_score += 10
        
        # Adjust for trends
        if trend_analysis['vulnerability_trend'] == 'increasing_risk':
            risk_score += 15
        elif trend_analysis['vulnerability_trend'] == 'decreasing_risk':
            risk_score -= 10
        
        # Determine risk level
        if risk_score >= 80:
            risk_level = 'critical'
        elif risk_score >= 60:
            risk_level = 'high'
        elif risk_score >= 40:
            risk_level = 'medium'
        else:
            risk_level = 'low'
        
        return {
            'risk_score': risk_score,
            'risk_level': risk_level,
            'risk_factors': {
                'high_click_rate': click_rate > 30,
                'high_data_entry': data_entry_rate > 15,
                'low_reporting': report_rate < 20,
                'high_vulnerability': avg_vulnerability > 70,
                'increasing_risk': trend_analysis['vulnerability_trend'] == 'increasing_risk'
            }
        }
    
    def generate_user_training_recommendations(self, risk_profile, trend_analysis):
        """Generate user training recommendations"""
        recommendations = []
        
        risk_level = risk_profile['risk_level']
        risk_factors = risk_profile['risk_factors']
        
        if risk_level == 'critical':
            recommendations.append({
                'type': 'immediate_intervention',
                'priority': 'critical',
                'description': 'Critical risk user - immediate intervention required',
                'actions': [
                    'One-on-one security training session',
                    'Additional phishing simulations',
                    'Regular follow-up assessments'
                ]
            })
        elif risk_level == 'high':
            recommendations.append({
                'type': 'intensive_training',
                'priority': 'high',
                'description': 'High-risk user - intensive training required',
                'actions': [
                    'Additional security awareness modules',
                    'Focused phishing training',
                    'Monthly assessments'
                ]
            })
        elif risk_level == 'medium':
            recommendations.append({
                'type': 'standard_training',
                'priority': 'medium',
                'description': 'Medium-risk user - standard training',
                'actions': [
                    'Regular security awareness training',
                    'Quarterly phishing simulations',
                    'Progress monitoring'
                ]
            })
        
        # Specific recommendations based on risk factors
        if risk_factors['high_click_rate']:
            recommendations.append({
                'type': 'click_prevention',
                'priority': 'high',
                'description': 'Specific training in identifying malicious links',
                'actions': ['Link analysis training', 'URL verification techniques']
            })
        
        if risk_factors['high_data_entry']:
            recommendations.append({
                'type': 'data_protection',
                'priority': 'critical',
                'description': 'Critical data protection training',
                'actions': ['Data handling training', 'Credential protection training']
            })
        
        if risk_factors['low_reporting']:
            recommendations.append({
                'type': 'reporting_improvement',
                'priority': 'medium',
                'description': 'Improve incident reporting culture',
                'actions': ['Reporting process training', 'Incentive programs']
            })
        
        if risk_factors['increasing_risk']:
            recommendations.append({
                'type': 'trend_intervention',
                'priority': 'high',
                'description': 'Intervention to reverse increasing risk trend',
                'actions': ['Intensive retraining', 'Behavioral coaching']
            })
        
        return recommendations

# Usage example
behavior_analysis = BehaviorAnalysis()

# Simulate user simulation history
user_simulation_history = [
    {
        'simulation_id': 'SIM-1',
        'sent_date': datetime.now() - timedelta(days=30),
        'link_clicked': True,
        'reported_phishing': False,
        'data_entered': True,
        'vulnerability_score': 85
    },
    {
        'simulation_id': 'SIM-2',
        'sent_date': datetime.now() - timedelta(days=20),
        'link_clicked': True,
        'reported_phishing': False,
        'data_entered': False,
        'vulnerability_score': 75
    },
    {
        'simulation_id': 'SIM-3',
        'sent_date': datetime.now() - timedelta(days=10),
        'link_clicked': False,
        'reported_phishing': True,
        'data_entered': False,
        'vulnerability_score': 45
    }
]

# Analyze user behavior
user_analysis = behavior_analysis.analyze_user_behavior('USER-001', user_simulation_history)
print(f"User analysis: {user_analysis['risk_profile']['risk_level']}")
print(f"Click rate: {user_analysis['click_rate']:.1f}%")
print(f"Recommendations: {len(user_analysis['training_recommendations'])}")