Document Forensics

Document Fraud Risk Calculator

Estimate how much undetected document fraud is costing your business each year.

Risk and fraud leadersCFOs and finance operationsCompliance officers building business casesFounders evaluating verification ROI
4.9·132+ reviews

Check a document instantly

Upload a file to start verification.

Drag & drop your document

or click to browse

PNG, JPG, WebP, PDF · Max 10MB

Your file stays in your browser until you create an account and confirm your email. Originals are deleted after analysis.

Advanced Verification
Originals Deleted
Redacted Reports

TrueDoc ROI and performance stats

<120sForensic report
10× fasterFraud review
40+Fraud signals
8+ hrsSaved / 100 docs

Estimated savings based on replacing a 10–15 minute manual document review with automated TrueDoc analysis.

Built on Trusted AI Infrastructure
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic
Google Cloud
Gemini
OpenAI
Anthropic

Multi-layer forensic logic

Proprietary detection scans template variance, metadata drift, pixel-level retouching, and structural anomalies the human eye misses.

▸ Document Analysis · LiveID: 8829-XQ
Risk score: High · 94%Signals matched: 12,042

Metadata deep-dive

Inspects EXIF, software signatures, edit history, and structural fingerprints.

SoftwareAdobe Photoshop 2024
ModifiedDetected
Geo-tagMismatch

Privacy-first by design

Originals are processed in encrypted memory and removed after analysis. Reports stay redacted by default.

No training on your data
Team & admin controls
▸ 01 · The Problem

Why eyeballing a document no longer works

Most teams underestimate document fraud because losses are spread across charge-offs, evictions, voided contracts, and clawbacks — never aggregated under a single line item.

A simple model — volume × fraud rate × average loss — usually surfaces a six- or seven-figure annual exposure, often justifying automated verification on its own.

▸ 02 · Fraud Signals

What we look for

Cross-checked across 5+ vectors
▸ Primary signal

Loan defaults driven by fake income docs

Detected at pixel + metadata + structural layers

Tenancy losses from forged pay stubs and IDs

Insurance payouts on tampered claims

Vendor payments routed to fake invoices

KYC failures triggering regulatory fines

What gets checked

Income proofs (pay stubs, statements)
Identity documents (IDs, passports)
Invoices and receipts
Insurance and claim documentation
Employment and address verification
▸ 03 · Workflow

From upload to verdict

01

Estimate document volume

How many documents do you review per month?

02

Pick your fraud rate

Industry baselines: 1–3% lending, 3–6% rental, 5–10% insurance claims.

03

Enter average loss per case

Include direct loss + recovery and operational cost.

04

See annual exposure

Multiply through to a yearly number — then compare against verification cost.

How the document fraud risk calculator differs from a generic AI check

Most "AI detector" tools look at one signal — usually a perplexity score on extracted text. The document fraud risk calculator runs that as one layer of many. It also evaluates metadata lineage (software, edit history, geo), pixel-level forensics (ELA, font kerning, retouching regions), and structural anomalies in the underlying PDF or image container.

The reason: loan defaults driven by fake income docs rarely leaves only one fingerprint. A convincing forgery usually fails on two or three of those layers, even when one of them looks clean.

What a high-risk report actually shows

A high-risk verdict on Income proofs (pay stubs, statements), Identity documents (IDs, passports), Invoices and receipts returns per-field evidence — not just a score. You see the suspicious regions highlighted on the page, the specific metadata fields that triggered the flag (for example, "Tenancy losses from forged pay stubs and IDs"), and the layer each finding came from.

That structure is what makes the verdict actionable: risk and fraud leaders can read why a document was flagged before deciding to reject, request a reupload, or escalate.

Common false positives and how we suppress them

Scanned originals, mobile-camera shots, and re-exported PDFs are the three most common sources of benign anomalies. The document fraud risk calculator scores those differently from the patterns associated with deliberate forgery — for example, a recompressed JPEG from a phone is not treated the same as a recompressed JPEG with a font substitution.

When a document is flagged, the report tells you which signal triggered it. If the only signal is a low-confidence compression artifact, the verdict is downgraded rather than counted as fraud.

Run a real document. Get a forensic verdict.

No credit card. Redacted report in under a minute.

▸ FAQ

Frequently asked questions