Synthetic Data Generation

"""
Synthetic Data Generator for Deception Environments.
Generates realistic-looking data for seeding decoy databases,
file shares, and applications. All data is entirely synthetic -
no real PII is used.
"""
from faker import Faker
import json
import csv
import random
import hashlib
import io
from datetime import datetime, timedelta

fake = Faker()
Faker.seed(42)  # Reproducible but realistic output

def generate_customer_records(count=500):
    """Generate synthetic customer records for a decoy database."""
    records = []
    for i in range(count):
        created = fake.date_time_between(start_date="-3y", end_date="now")
        records.append({
            "customer_id": f"CUS-{10000 + i}",
            "first_name": fake.first_name(),
            "last_name": fake.last_name(),
            "email": fake.company_email(),
            "phone": fake.phone_number(),
            "address": fake.street_address(),
            "city": fake.city(),
            "state": fake.state_abbr(),
            "zip": fake.zipcode(),
            "account_type": random.choice([
                "checking", "savings", "business", "premium"
            ]),
            "balance": round(random.uniform(100, 250000), 2),
            "created_at": created.isoformat(),
            "last_login": (
                created + timedelta(days=random.randint(1, 365))
            ).isoformat(),
            "status": random.choices(
                ["active", "inactive", "suspended"],
                weights=[85, 10, 5],
            )[0],
        })
    return records

def generate_employee_directory(count=150):
    """Generate synthetic employee directory for AD-like data."""
    departments = [
        "Engineering", "Finance", "HR", "Legal", "Marketing",
        "Operations", "Sales", "IT", "Security", "Executive",
    ]
    titles = {
        "Engineering": ["Software Engineer", "Senior Developer",
                        "Tech Lead", "DevOps Engineer"],
        "Finance": ["Financial Analyst", "Controller",
                     "Accounts Manager", "CFO"],
        "IT": ["Systems Administrator", "Network Engineer",
               "Help Desk", "IT Manager"],
        "Security": ["Security Analyst", "SOC Analyst",
                      "CISO", "Threat Hunter"],
    }

    employees = []
    for i in range(count):
        dept = random.choice(departments)
        first = fake.first_name()
        last = fake.last_name()
        username = f"{first[0].lower()}.{last.lower()}"
        employees.append({
            "employee_id": f"EMP-{2000 + i}",
            "username": username,
            "email": f"{username}@corp.internal",
            "first_name": first,
            "last_name": last,
            "department": dept,
            "title": random.choice(
                titles.get(dept, ["Analyst", "Manager", "Director"])
            ),
            "manager": fake.name(),
            "office": f"Building {random.choice('ABC')}-"
                      f"{random.randint(1,5)}{random.randint(0,30):02d}",
            "phone_ext": str(random.randint(1000, 9999)),
            "hire_date": fake.date_between(
                start_date="-10y", end_date="-30d"
            ).isoformat(),
            "status": "active",
        })
    return employees

def generate_network_config_files():
    """Generate realistic network configuration files with trap data."""
    configs = {
        "database.env": """# Production Database Configuration
# Auto-generated by deployment pipeline
DB_HOST=prod-db-01.corp.internal
DB_PORT=5432
DB_NAME=customerdb
DB_USER=app_svc_prod
DB_PASS=Pr0d-Db#2026!xK9m
DB_SSL=require
DB_POOL_SIZE=25
REDIS_URL=redis://cache-01.corp.internal:6379/0
""",
        ".aws/credentials": """[default]
aws_access_key_id = AKIAIOSFODNN7EXAMPLE
aws_secret_access_key = wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
region = us-east-1

[prod-deploy]
aws_access_key_id = AKIAI44QH8DHBEXAMPLE
aws_secret_access_key = je7MtGbClwBF/2Zp9Utk/h3yCo8nvbEXAMPLEKEY
region = us-east-1
""",
        "backup-config.sh": """#!/bin/bash
# Nightly backup script - runs via cron at 02:00
BACKUP_USER="backup_svc"
BACKUP_PASS="B4ckup#Nightly_2026"
BACKUP_HOST="nas-01.corp.internal"
BACKUP_PATH="/mnt/backups/production"

pg_dump -h prod-db-01.corp.internal \
  -U $BACKUP_USER -d customerdb \
  | gzip > "$BACKUP_PATH/db_$(date +%Y%m%d).sql.gz"
""",
    }
    return configs

if __name__ == "__main__":
    # Generate all synthetic data
    customers = generate_customer_records(500)
    employees = generate_employee_directory(150)
    configs = generate_network_config_files()

    # Output customer records as CSV
    output = io.StringIO()
    writer = csv.DictWriter(output, fieldnames=customers[0].keys())
    writer.writeheader()
    writer.writerows(customers)
    with open("synthetic_customers.csv", "w") as f:
        f.write(output.getvalue())

    # Output employee directory as JSON
    with open("synthetic_employees.json", "w") as f:
        json.dump(employees, f, indent=2)

    # Output config files
    for filename, content in configs.items():
        safe_name = filename.replace("/", "_").replace(".", "_")
        with open(f"decoy_{safe_name}", "w") as f:
            f.write(content)

    print(f"Generated {len(customers)} customer records")
    print(f"Generated {len(employees)} employee records")
    print(f"Generated {len(configs)} config files with trap credentials")