Home/Guides/Detect Forged Passports & IDs
Identity Fraud
AI can generate a passport page with correct MRZ data from a text prompt. Visual inspection can't stop that.
Identity document fraud has moved from physical forgeries to digital fabrication. AI-generated passports include realistic security patterns, correct MRZ data, and convincing portraits. Photo substitution on genuine documents is seamless to the naked eye. The only defence is forensic analysis at the pixel level - checking noise patterns, boundary artifacts, and the signatures that separate real government printing from machine generation.
- No document storage
- Digital, scanned or photographed
- ~1 minute per verdict
Last updated:
The problem
How ID fraud evolved past visual checks
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
Check digits, character alignment, consistency between the MRZ data and the visual fields. AI-generated passports often get the relationships wrong.
Photo zone boundary analysis
Replace a portrait and the boundary shows contrast gradients, sharpness differences, and compression artifacts. Seamless to the eye, detectable forensically.
Security overlay plausibility
Holograms, guilloche patterns, UV-reactive elements - genuine security features that AI and edited documents replicate imperfectly. The patterns don't hold up under analysis.
Font and field consistency
Government IDs use specific typefaces, spacing, and field positions. Edit a date of birth or document number and the font metrics shift.
AI-generation detection
AI-generated IDs carry noise patterns, rendering artifacts, and structural properties that government printing systems don't produce.
Physical scan authenticity
Scanner noise, paper texture, edge properties - a genuine scan of a physical document reads differently from a digital fabrication.
The solution
Forensic verification for passports, IDs, and driver's licences
Upload a passport page, ID card, or driver's licence. Get back a forensic verdict with specific findings on every region - what's authentic, what's not.
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 fast via API or dashboard
- Zero document storage - critical for identity documents under GDPR
Why us
What you won't get elsewhere
Findings, not a score
We name the field that changed and where it sits on the page.
Others hand you a number to justify.
One endpoint, every type
100+ document types, 190+ countries, no per-type setup.
Elsewhere, each new form is a project.
Catches what was never real
A dedicated pass for AI-generated and deepfake documents.
Template matching only catches edits.
Nothing is retained
Analysed in memory, then discarded. Never trained on.
Most services keep documents for QA.
Live in minutes
Published pricing, no minimum. Test it before you talk to us.
Platforms want a contract first.
Sits alongside your stack
Keep Onfido or Jumio for face match. We add the forensics.
Not a rip-and-replace.
FAQ
Common questions
Does TamperCheck work on ID documents from any country?
The analysis targets forensic properties, not country-specific templates. Passports and IDs from any issuing authority - including documents it has never encountered before.
Can TamperCheck replace NFC chip verification?
No. NFC reading requires physical proximity to the document. TamperCheck is for remote verification - when the document arrives as a photo, scan, or PDF. Teams use both: NFC when the person is present, TamperCheck when the document is submitted digitally.
Is it safe to upload identity documents to TamperCheck?
Files are processed in memory and discarded immediately after analysis. Nothing is retained on our infrastructure. That's a core design constraint, not an opt-in setting.
Or skip the call entirely
We'll match your first top-up in credits, so you can run your own documents through it now.