PDF Tamper Detection Tool

Spot a tampered PDF before it costs you.

Reads the file. Not the page.

The structural PDF layer Plaid and Persona don’t cover — detect bank statements, payslips and invoices edited after they were issued.

63 forensic checks across metadata, file structure, and digital signatures — verdict in under 3 seconds.

Your file uploads to encrypted EU storage and is analysed at the byte level — we never read the page content, only the file structure. Web uploads may be kept in anonymized form to improve detection.

By continuing you accept our Terms & Conditions. Maximum PDF file size is 10 MB.

~3 sec verdict63 forensic checksAlgorithm v2.47.0 · updated 18.10.2026In production since October 20245 free credits on signup
Encrypted in TransitHTTPS/TLS
Anonymized for AnalysisNever tied to you
EU Data ResidencyStored in the EU
Content Never ReadStructure only
Private by DefaultOnly you see results
DPA AvailableGDPR processing terms

The detection gap

KYC platforms check the document. HTPBE? checks the file.

Two different checks – both matter.

KYC & identity platforms

Plaid · Persona · Alloy · Jumio

  • Is this a real bank statement template?
  • Does the account number match the identity?
  • Is the document format consistent with the issuing bank?

Detects fake documents. Does not detect edited real documents.

HTPBE? tamper detection API

Structural PDF integrity

  • Was this specific PDF file modified after it was generated?
  • Do metadata timestamps match the file structure?
  • Were digital signatures valid at the time of signing?

Catches edits invisible to visual review and template checks.

Results in under 3 secondsProcess 30 to 1,500+ documents/monthIn production since October 2024

Use Cases

One undetected edit costs more than a year of prevention

One API, three critical document workflows.

Primary for lending teams

Bank Statement Fraud Detection

Bank statement fraud detection for alt-lending: one approved loan on an edited statement becomes a default you can’t collect on. Catch edited balances and fabricated transaction histories before approving a loan application.

Learn more →

Invoice Fraud Detection

Invoice fraud detection for AP teams: BEC invoice scams average $130,000 per incident. Detect bank account swaps and amount changes in vendor invoices before payment is processed.

Learn more →

Certificate & Diploma Fraud Detection

Certificate fraud detection on hiring: one bad hire based on fake credentials costs $50K+ in recruiting, onboarding, and severance. Expose edited academic credentials and professional certificates submitted during hiring or onboarding.

Learn more →

Scale Your Fraud Detection

Your team processes hundreds of documents. Automate the integrity check.

One edited bank statement that slips through underwriting becomes an approved loan you can’t collect on. HTPBE? is a document fraud detection API running 63 tamper detection checks per document via REST — results in seconds, no original file needed.

HTPBE? detects fake documents like:bank statementspay stubstax formsinvoicesmany others

63 tamper detection checks

per document, across metadata, structure, and signatures

Under 3 seconds

per document at any volume – 30 to 1,500+/month

Works alongside your KYC stack

Plaid, Persona, Alloy – the structural layer they don’t cover

For AI coding agents

Integrate in one line

We publish a machine-readable skill file. Hand this command to your coding agent (Claude Code, Cursor, Codex) and it reads the endpoints, auth and verdict format, then writes the integration for you.

curl -s https://htpbe.tech/SKILL.md
View SKILL.md

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 checked 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

PDF Integrity Report

We Publish Monthly Integrity Findings From Real Documents

Every month HTPBE? reports the structural modification signals we see in documents submitted for analysis – with transparent methodology and downloadable source data.

Across documents submitted to HTPBE? for analysis, 64% of conclusively-analyzed files showed structural modification signals.

Submitted files are self-selected and are not representative of all PDFs.

Close the structural fraud gap

Create your account – API key on signup, free test environment on every plan.
No sales call. Cancel any time.

FAQ

Frequently Asked Questions

Get answers to common questions about PDF authenticity checking.

What is HTPBE?, and what does it do?

HTPBE? (Has This PDF Been Edited?) detects whether a PDF was modified after it was created. Upload a file of up to 10 MB and get a verdict — Intact, Modified or Inconclusive — with the findings behind it.

Read the full answer

What does HTPBE? stand for, and how do you pronounce it?

HTPBE? stands for “Has This PDF Been Edited?” Pronounce it letter by letter: H-T-P-B-E.

Read the full answer

How is HTPBE? different from KYC platforms like Onfido or Persona?

KYC platforms confirm who a person is. HTPBE? checks whether a specific PDF file was modified after it was generated. An identity can be real while a supporting document has been edited, so the two checks complement each other.

Read the full answer

What does the API response look like?

The API returns JSON with a status of intact, modified or inconclusive, plus the named HTPBE_ markers behind a modified verdict. There is no numeric score — every verdict is explained. Analyze returns an id; the result endpoint returns the full object.

Read the full answer

How much does each document check cost?

Every check costs one credit, from the web app or the API — both use the same balance. You fund it with a monthly plan (from $15 for 30 credits), a one-time pack ($5 for 8, $15 for 25) or the 5 free credits every new account gets. Test API keys are free.

Read the full answer

Do you offer test API keys?

Yes. Test keys (htpbe_test_...) are free, unlimited and available on every plan, even before you subscribe. They return deterministic synthetic results for predefined test URLs and never use credits. They cannot analyze real documents.

Read the full answer