Skip to main content
FlexOrch scans every document for personal and sensitive data before it enters a dataset. Detected PII is automatically masked in the output, so your training data stays clean without requiring a separate privacy pipeline. Detection covers 46 PII types across Turkish, EU, and US jurisdictions.

​
Detected Types

​
Universal

TypeDescription
emailEmail addresses
credit_cardCredit card numbers (all major schemes, Luhn-validated)
ipIPv4 addresses
ip_v6IPv6 addresses
ibanInternational bank account numbers (mod-97 validated)

​
Turkey (TR)

TypeDescription
national_id_trT.C. Kimlik No (11 digits)
tax_id_trVergi Kimlik No (10 digits, VKN)
phone_trTurkish mobile and landline numbers
iban_trTurkish IBANs (TR prefix, 26 chars)
emeklilik_noSGK Emeklilik sicil no
isyeri_sicil_noSGK İşyeri sicil no
bagkur_noBağ-Kur sicil no

​
Germany (DE)

TypeDescription
national_id_dePersonalausweis number
tax_id_deSteueridentifikationsnummer (11 digits)
phone_deGerman phone numbers
iban_deGerman IBANs (DE prefix)

​
France (FR)

TypeDescription
national_id_frNuméro de sécurité sociale (15 digits)
tax_id_frNuméro SPI / NIF
phone_frFrench phone numbers
iban_frFrench IBANs (FR prefix)

​
Italy (IT)

TypeDescription
national_id_itCodice Fiscale (alphanumeric)
phone_itItalian phone numbers
iban_itItalian IBANs (IT prefix)

​
Netherlands (NL)

TypeDescription
national_id_nlBurgerservicenummer (BSN, 9 digits)
tax_id_nlBTW-nummer
phone_nlDutch phone numbers

​
Spain (ES)

TypeDescription
national_id_esDNI / NIE
tax_id_esNIF
phone_esSpanish phone numbers

​
Poland (PL)

TypeDescription
national_id_plPESEL (11 digits)
tax_id_plNIP (10 digits)
phone_plPolish phone numbers

​
United Kingdom (UK) & United States (US)

TypeDescription
national_id_ukNational Insurance Number (NINO)
ssn_usSocial Security Number
phone_ukUK phone numbers
phone_usUS phone numbers

​
Additional EU Jurisdictions

National ID and phone types are also covered for Austria, Belgium, Sweden, Denmark, Finland, and Portugal.

​
Masking Strategies

When PII is detected, FlexOrch replaces each finding with a placeholder. The default strategy is redact:
StrategyOutput ExampleUse Case
redact[MASKED_EMAIL]Production datasets, LLM fine-tuning
replaceperson@example.comTesting with plausible synthetic data
token<EMAIL_1>Preserving structure for NLP tasks
hasha3f2b1...Deterministic anonymization

​
API Response

After processing, PII information is available in the job response: 
{
  "pii_findings_count": 4,
  "privacy_applied": true,
  "processing_summary": {
    "pii_type_summary": {
      "email": 2,
      "national_id_tr": 1,
      "iban": 1
    }
  }
}
The full type breakdown is also included in the dataset profile: 
curl https://api.flexorch.com/v1/datasets/{id}/profile \
  -H "X-API-KEY: dfx_your_key_here"

​
KVKK & GDPR Compliance

FlexOrch generates a compliance report for every dataset. The profile endpoint returns:
  • gdpr_categories — GDPR Article 9 special category flags
  • detected_countries — Jurisdictions found in the data
  • applicable_regulations — KVKK, GDPR, NIS2, eIDAS as relevant
curl https://api.flexorch.com/v1/datasets/{id}/profile \
  -H "X-API-KEY: dfx_your_key_here"
For a GDPR Article 30 Record of Processing Activities (ROPA), use the compliance endpoint: 
curl https://api.flexorch.com/v1/compliance/record \
  -H "X-API-KEY: dfx_your_key_here"

​
Open Source

PII detection is also available as a standalone, zero-dependency package — no FlexOrch account required. See flexorch-audit for installation and usage.