# Enable Amazon Macie
aws macie2 enable-macie
 
# List all S3 buckets Macie can scan
aws macie2 describe-buckets \
  --query 'buckets[*].[bucketName,classifiableSizeInBytes,unclassifiableObjectCount.total]' \
  --output table
 
# Create a classification job for specific buckets
aws macie2 create-classification-job \
  --job-type SCHEDULED \
  --name "weekly-pii-scan" \
  --schedule-frequency-details '{"weekly":{"dayOfWeek":"MONDAY"}}' \
  --s3-job-definition '{
    "bucketDefinitions": [{
      "accountId": "ACCOUNT_ID",
      "buckets": ["customer-data-bucket", "analytics-data-lake", "backup-bucket"]
    }],
    "scoping": {
      "includes": {
        "and": [{
          "simpleScopeTerm": {
            "key": "OBJECT_EXTENSION",
            "values": ["csv", "json", "parquet", "txt", "xlsx"],
            "comparator": "EQ"
          }
        }]
      }
    }
  }' \
  --managed-data-identifier-ids '["SSN","CREDIT_CARD_NUMBER","EMAIL_ADDRESS","AWS_CREDENTIALS","PHONE_NUMBER"]'
 
# Create custom data identifier for internal employee IDs
aws macie2 create-custom-data-identifier \
  --name "EmployeeID" \
  --regex "EMP-[0-9]{6}" \
  --description "Internal employee ID format"
 
# Check job status and results
aws macie2 list-classification-jobs \
  --query 'items[*].[name,jobStatus,statistics.approximateNumberOfObjectsToProcess]' \
  --output table

# Inspect a Cloud Storage bucket for sensitive data
gcloud dlp inspect-content \
  --content-type=TEXT_PLAIN \
  --min-likelihood=LIKELY \
  --info-types=PHONE_NUMBER,EMAIL_ADDRESS,CREDIT_CARD_NUMBER,US_SOCIAL_SECURITY_NUMBER \
  --storage-type=CLOUD_STORAGE \
  --gcs-uri="gs://sensitive-data-bucket/data/*.csv"
 
# Create an inspection job for BigQuery
cat > dlp-job.json << 'EOF'
{
  "inspectJob": {
    "storageConfig": {
      "bigQueryOptions": {
        "tableReference": {
          "projectId": "PROJECT_ID",
          "datasetId": "customer_data",
          "tableId": "transactions"
        },
        "sampleMethod": "RANDOM_START",
        "rowsLimit": 10000
      }
    },
    "inspectConfig": {
      "infoTypes": [
        {"name": "CREDIT_CARD_NUMBER"},
        {"name": "US_SOCIAL_SECURITY_NUMBER"},
        {"name": "EMAIL_ADDRESS"},
        {"name": "PHONE_NUMBER"},
        {"name": "PERSON_NAME"}
      ],
      "minLikelihood": "LIKELY",
      "limits": {"maxFindingsPerRequest": 1000}
    },
    "actions": [{
      "saveFindings": {
        "outputConfig": {
          "table": {
            "projectId": "PROJECT_ID",
            "datasetId": "dlp_results",
            "tableId": "findings"
          }
        }
      }
    }]
  }
}
EOF
 
gcloud dlp jobs create --project=PROJECT_ID --body-from-file=dlp-job.json

# deidentify_pipeline.py - De-identify sensitive data using Google Cloud DLP
from google.cloud import dlp_v2
 
def deidentify_data(project_id, text):
    """De-identify PII in text using Cloud DLP."""
    client = dlp_v2.DlpServiceClient()
 
    inspect_config = {
        "info_types": [
            {"name": "EMAIL_ADDRESS"},
            {"name": "PHONE_NUMBER"},
            {"name": "CREDIT_CARD_NUMBER"},
            {"name": "US_SOCIAL_SECURITY_NUMBER"},
        ],
        "min_likelihood": dlp_v2.Likelihood.LIKELY,
    }
 
    deidentify_config = {
        "info_type_transformations": {
            "transformations": [
                {
                    "info_types": [{"name": "EMAIL_ADDRESS"}],
                    "primitive_transformation": {
                        "character_mask_config": {
                            "masking_character": "*",
                            "number_to_mask": 0,
                            "characters_to_ignore": [
                                {"common_characters_to_ignore": "PUNCTUATION"}
                            ],
                        }
                    },
                },
                {
                    "info_types": [{"name": "CREDIT_CARD_NUMBER"}],
                    "primitive_transformation": {
                        "crypto_replace_ffx_fpe_config": {
                            "crypto_key": {
                                "kms_wrapped": {
                                    "wrapped_key": "WRAPPED_KEY_BASE64",
                                    "crypto_key_name": "projects/PROJECT/locations/global/keyRings/dlp/cryptoKeys/tokenization",
                                }
                            },
                            "common_alphabet": "NUMERIC",
                        }
                    },
                },
                {
                    "info_types": [{"name": "US_SOCIAL_SECURITY_NUMBER"}],
                    "primitive_transformation": {
                        "redact_config": {}
                    },
                },
            ]
        }
    }
 
    item = {"value": text}
    parent = f"projects/{project_id}/locations/global"
 
    response = client.deidentify_content(
        request={
            "parent": parent,
            "deidentify_config": deidentify_config,
            "inspect_config": inspect_config,
            "item": item,
        }
    )
    return response.item.value

# Connect to Microsoft Purview compliance
Connect-IPPSSession
 
# Create sensitivity labels
New-Label -DisplayName "Confidential - PII" \
  -Name "Confidential-PII" \
  -Tooltip "Contains personally identifiable information" \
  -ContentType "File, Email"
 
New-Label -DisplayName "Highly Confidential - Financial" \
  -Name "HighlyConfidential-Financial" \
  -Tooltip "Contains financial data subject to PCI DSS" \
  -ContentType "File, Email"
 
# Create auto-labeling policy for Azure Storage
New-AutoSensitivityLabelPolicy -Name "Auto-Label-PII" \
  -ExchangeLocation All \
  -SharePointLocation All \
  -OneDriveLocation All \
  -Mode Enable
 
New-AutoSensitivityLabelRule -Policy "Auto-Label-PII" \
  -Name "Detect-SSN" \
  -ContentContainsSensitiveInformation @{
    Name = "U.S. Social Security Number (SSN)";
    MinCount = 1;
    MinConfidence = 85
  } \
  -ApplySensitivityLabel "Confidential-PII"

# Azure: Configure DLP policy for Storage accounts
az security assessment create \
  --name "storage-sensitive-data" \
  --assessed-resource-type "Microsoft.Storage/storageAccounts"
 
# Enable Microsoft Defender for Storage with sensitive data threat detection
az security pricing create --name StorageAccounts --tier standard \
  --subplan DefenderForStorageV2 \
  --extensions '[{"name":"SensitiveDataDiscovery","isEnabled":"True"}]'

# pipeline_dlp_gate.py - DLP gate for data pipelines
import boto3
import json
 
macie_client = boto3.client('macie2')
s3_client = boto3.client('s3')
 
def scan_pipeline_output(bucket, prefix):
    """Scan pipeline output data for sensitive content before promotion."""
    job_response = macie_client.create_classification_job(
        jobType='ONE_TIME',
        name=f'pipeline-scan-{prefix}',
        s3JobDefinition={
            'bucketDefinitions': [{
                'accountId': boto3.client('sts').get_caller_identity()['Account'],
                'buckets': [bucket]
            }],
            'scoping': {
                'includes': {
                    'and': [{
                        'simpleScopeTerm': {
                            'key': 'OBJECT_KEY',
                            'comparator': 'STARTS_WITH',
                            'values': [prefix]
                        }
                    }]
                }
            }
        },
        managedDataIdentifierSelector='ALL'
    )
 
    return job_response['jobId']
 
def check_scan_results(job_id):
    """Check if DLP scan found sensitive data."""
    response = macie_client.list_findings(
        findingCriteria={
            'criterion': {
                'classificationDetails.jobId': {'eq': [job_id]},
                'severity.description': {'eq': ['High', 'Critical']}
            }
        }
    )
    return len(response.get('findingIds', [])) > 0
 
def gate_decision(bucket, prefix):
    """DLP gate: block pipeline if sensitive data found."""
    job_id = scan_pipeline_output(bucket, prefix)
    has_sensitive_data = check_scan_results(job_id)
 
    if has_sensitive_data:
        return {
            'decision': 'BLOCK',
            'reason': 'Sensitive data detected in pipeline output',
            'action': 'Apply de-identification before promoting to production'
        }
    return {'decision': 'ALLOW', 'reason': 'No sensitive data detected'}

# Macie: Get finding statistics
aws macie2 get-finding-statistics \
  --group-by "severity.description" \
  --finding-criteria '{"criterion":{"category":{"eq":["CLASSIFICATION"]}}}'
 
# Macie: List findings by sensitivity type
aws macie2 list-findings \
  --finding-criteria '{
    "criterion": {
      "classificationDetails.result.sensitiveData.category": {"eq": ["PERSONAL_INFORMATION"]},
      "severity.description": {"eq": ["High"]}
    }
  }' \
  --sort-criteria '{"attributeName": "updatedAt", "orderBy": "DESC"}'
 
# GCP DLP: List job results
gcloud dlp jobs list --project=PROJECT_ID --filter="state=DONE" \
  --format="table(name, createTime, inspectDetails.result.processedBytes, inspectDetails.result.totalEstimatedTransformations)"
 
# Export Macie findings to S3 for compliance reporting
aws macie2 create-findings-report \
  --finding-criteria '{"criterion":{"category":{"eq":["CLASSIFICATION"]}}}' \
  --sort-criteria '{"attributeName":"severity.score","orderBy":"DESC"}'

Cloud DLP Compliance Report
==============================
Organization: Acme Corp
Scan Period: 2026-02-01 to 2026-02-23
Environments: AWS (12 buckets), GCP (3 datasets), Azure (5 storage accounts)
 
DATA DISCOVERY SUMMARY:
  Total objects/records scanned:    2,847,000
  Objects with sensitive data:        45,200 (1.6%)
  Unique sensitivity categories:      8
 
SENSITIVE DATA FINDINGS:
  PII (names, emails, phone):       23,400 objects
  Financial (credit cards, bank):     8,700 objects
  Health (PHI, medical records):      3,200 objects
  Credentials (API keys, tokens):     1,400 objects
  Government ID (SSN, passport):      5,800 objects
  Custom (employee ID, account):      2,700 objects
 
FINDINGS BY SEVERITY:
  Critical:    1,400 (exposed credentials)
  High:       14,200 (unprotected PII/PHI)
  Medium:     18,600 (standard PII)
  Low:        11,000 (non-sensitive patterns)
 
PROTECTION STATUS:
  Data with encryption at rest:       78%
  Data with access controls:          65%
  Data with sensitivity labels:       12%
  Pipeline data with DLP gates:       30%
 
REMEDIATION ACTIONS:
  Objects quarantined:                1,400
  De-identification applied:          8,200
  Access controls tightened:         14,200
  Sensitivity labels applied:        45,200