Forged passports and fake IDs are getting better. Your detection needs to keep up.
AI-generated identity documents now include realistic security features, correct MRZ data, and convincing photo zones. Traditional visual inspection is no longer sufficient. TamperCheck provides forensic analysis of passports, ID cards, and driver's licences — detecting tampering, fabrication, and AI generation at the pixel level.
The problem
The identity document fraud landscape
Identity document fraud has evolved from crude physical forgeries to sophisticated digital fabrication. AI tools can generate a convincing passport page complete with MRZ data, security patterns, and a realistic portrait — all from a text description.
The most dangerous technique is photo zone substitution on genuine documents. The document itself is authentic; only the portrait has been replaced. The edges of the replacement are seamless to the naked eye but leave boundary contrast signatures that forensic analysis detects.
Remote onboarding has made the problem worse. When identity documents are submitted as photos or scans rather than presented in person, there's no opportunity to check physical security features (UV, watermarks, chip). The only defence is digital forensic analysis of the submitted image or PDF.
What we detect
Forensic signals that expose fraud
MRZ line integrity
The Machine Readable Zone encodes name, nationality, document number, and dates. TamperCheck verifies check digit accuracy, character alignment, and consistency between MRZ data and the visual fields on the document.
Photo zone boundary analysis
When a portrait is replaced, the boundary between the new photo and the original background shows contrast gradients, sharpness differences, and compression artifacts that TamperCheck detects.
Security overlay plausibility
Genuine documents have security overlays (holograms, guilloche patterns, UV-reactive elements) that AI-generated and edited documents replicate imperfectly. TamperCheck analyses these patterns.
Font and field consistency
Government-issued documents use specific typefaces, spacing, and field positions. Edits to date of birth, document number, or expiry dates leave font metric anomalies.
AI-generation detection
AI-generated identity documents have characteristic noise patterns, rendering artifacts, and structural properties that distinguish them from documents produced by government printing systems.
Physical scan authenticity
When a scanned document is submitted, TamperCheck analyses scanner noise, paper texture, and edge properties to verify that it's a genuine scan of a physical document rather than a digital fabrication.
The solution
How TamperCheck verifies passports and IDs
Upload a passport page, ID card, or driver's licence — as a PDF, scan, or phone photo — and TamperCheck returns a forensic verdict with specific findings about what looks authentic and what doesn't.
How it works
- MRZ verification with check digit and field consistency analysis
- Photo zone forensics detecting portrait substitution and splicing
- Security feature analysis for holograms, overlays, and patterns
- Works on scans and photos — not just native digital documents
- Verdict in seconds via API or dashboard
- Zero document storage — critical for identity documents under GDPR
FAQ
Common questions
See it working on your documents
Start with $5 in free credits — no contract, no card required. Upload your first document and get a verdict in seconds.