What data types and content can Siberson Veriket Data Discovery detect?
Siberson Veriket Data Discovery applies a multi-layered content inspection engine that combines pattern matching, data-shape validation, dictionaries, exact data matching (EDM), OCR, and AI-assisted classifiers. Out of the box it detects:
| Detection Family | Examples |
|---|---|
| Personal Identifiers (PII) | TC Kimlik No, passport numbers, national ID numbers, driver licenses, full names paired with addresses or dates of birth |
| Financial Data | Credit card numbers (PCI scope), IBANs, SWIFT codes, banking statements, invoice formats |
| Health Data | Patient identifiers, diagnostic codes (ICD-10), lab result formats, prescription patterns |
| Legal & Government | Tax IDs, court case numbers, citizen lookup IDs, regulatory filing identifiers |
| Intellectual Property | Source code patterns, design files, contract templates, fingerprinted documents (exact match) |
| Authentication Material | API keys, private keys, certificates, hard-coded credentials in source files |
| Custom Classifiers | Customer-defined regex, dictionaries, keyword packs, and trained AI classifiers for industry-specific data |
All detection runs against 400+ supported file types including Microsoft Office (legacy and OOXML), PDF, OpenDocument, image formats with OCR (PNG, JPEG, TIFF, scanned PDFs), email containers (PST, OST, EML, MSG), source code, archives (ZIP, 7z, RAR), and structured database content.
Last updated: 2026-04-29