logo
For fraud ops

The invoice came from a vendor you’ve paid for three years. One field was changed before it reached you

Invoice fraud rarely looks like fraud. A familiar vendor, a familiar layout, one edited bank account line. By the time the wire clears, the payment is gone.

~3 sec
per document
35 checks
forensic layers
From $15
per month
1,500+
docs / month on Growth
Scope

HTPBE analyzes the structural layer of the PDF file — the layer that records every edit, even invisible ones. We don’t inspect holograms, phone photos, or ID biometrics. If your fraud problem is a digitally altered PDF, we’re the most specific tool for it.

How it looks

One REST call, one deterministic verdict

Upload the PDF. The API returns INTACT, MODIFIED, or INCONCLUSIVE with named markers — in about three seconds.

What this looks like

Invoice Fraud document fraud in 2026

Three real fraud mechanics we catch at the structural PDF layer.

01

Swapped payment details

An intercepted or copied invoice is re-saved with a new bank account, IBAN, or routing number. The layout is identical — the file structure now carries an edit trail.

02

Inflated amounts

Line items or totals modified to skim additional funds. Arithmetic across subtotal, tax, and total lines stops reconciling when one figure is changed.

03

Fabricated supplier brand

A PDF that mimics a real vendor’s branding but was never issued by them. Producer metadata, font subsets, and layout consistency expose the forgery.

The scale of the problem

$2.7B+
lost to business email compromise and invoice fraud annually
1 in 4
finance teams report at least one invoice fraud incident per year
~3 sec
to verify an invoice PDF via API

The verification gap

KYC platforms verify the document. HTPBE verifies the file.

Two different checks — both matter.

OCR-based AP automation reads what the PDF shows. It doesn’t know whether the PDF was edited. Vendor-verification databases flag unknown suppliers; they say nothing about a known supplier’s invoice being tampered with in transit. HTPBE reads the file structure itself — the layer that records every modification regardless of how the content looks.

Results in under 3 seconds30 to 1,500+ documents/monthFrom $15/mo
How it works

Five forensic layers, one deterministic verdict

Every PDF we receive passes through the same structural pipeline — no model training, no thresholds to tune.

01

Metadata analysis

Creation and modification timestamps, producer and creator fields, XMP metadata — the first layer exposes basic tampering.

02

File structure

Xref tables, trailer chain, incremental updates. Any edit after export leaves a structural fingerprint here.

03

Digital signatures

Signature chain integrity and post-signature modifications produce deterministic markers. Certainty-level signal.

04

Content integrity

Fonts, objects, embedded content, page assembly. Multi-session edits and inserted objects are visible at this layer.

05

Verdict with markers

Deterministic output: INTACT / MODIFIED / INCONCLUSIVE, with named markers for every finding — suitable for audit trail.

Document types

PDF document types we verify for invoice fraud

Every type listed below is analyzed at the structural file layer — not the rendered image.

Vendor invoice PDFPurchase order PDFDelivery note PDFPayment confirmation PDFRemittance advice PDFCredit note PDF
What HTPBE checks

Detection capabilities

Deterministic structural signals. No probabilistic scores, no model training.

Arithmetic reconciliation

Line-item totals, tax, and grand totals are checked for internal consistency — one altered figure breaks the chain.

Incremental update detection

Any save after the original export creates a detectable update section in the PDF structure, even when the edit was one character.

Producer field mismatch

Authentic accounting software (QuickBooks, Xero, SAP, NetSuite) leaves a known producer signature. Re-saves through editors change it.

Object and font consistency

Edited objects and injected text reveal themselves through font subset prefix shifts and object-number anomalies.

Signature and timestamp checks

If the invoice was digitally signed, we verify the signature state and flag modifications applied after signing.

Customer Stories

Teams that stopped document fraud

Compliance, finance, and risk teams use HTPBE to catch manipulated PDFs before they become costly mistakes.

Caught an invoice where the total had been changed by less than a thousand dollars. Without this I would have approved it without a second look.

Sarah M.

AP Manager

United States

We had three applicants in the same week with bank statements that looked completely fine. Two of them were flagged as modified. You simply cannot see this by reading the document — it is in the file structure.

Lars V.

Risk Analyst, Online Lending

Netherlands

Salary slips were coming with altered figures. We identified two problematic files before the placement was finalised.

Priya K.

HR Operations Lead

India

Since we started checking documents this way, we stopped two applications early in the process that would have been very difficult to reverse later.

Julien R.

Fraud Analyst, Fintech

France

Some applicants were sending PDFs that looked authentic but had been edited in ways not visible to the eye. We now ask for verified originals when something is flagged. Already saved us from a few bad decisions.

Marta S.

Compliance Coordinator

Spain

One invoice was caught because there was a mismatch between the document dates and structure. That particular case would have cost us significantly.

Tariq A.

Finance Manager

United Arab Emirates

FAQ

Frequently asked questions

We detect structural modifications. Benign re-saves (for example, a vendor re-exporting after a typo fix) will be flagged as MODIFIED, not INTACT. The verdict is deterministic and paired with named markers, so your review team can decide what to do with each case.

OCR reads what’s visible. It cannot tell whether the PDF was edited after creation. HTPBE ignores the content and analyzes the file structure. Both are useful — OCR extracts, HTPBE verifies integrity.

It closes the last-mile attack. Most BEC fraud ends with a swapped payment detail on an otherwise legitimate invoice. HTPBE detects the swap at the structural layer, where the edit is recorded regardless of visible appearance.

That’s still fine. An original export from a known accounting tool produces a recognizable producer signature and no incremental update trail. Fresh authentic exports return INTACT.

Secure your workflow

Create your account — API key on signup, free test environment on every plan.
From $15/mo. No sales call. Cancel any time.