KYC verifies the person. HTPBE verifies the paperwork behind them
Identity-verification platforms confirm the face and the ID. They don’t examine the utility bill, bank letter, or certificate of incorporation the applicant uploaded. We do — at the structural PDF layer.
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.
One REST call, one deterministic verdict
Upload the PDF. The API returns INTACT, MODIFIED, or INCONCLUSIVE with named markers — in about three seconds.
KYC & Onboarding document fraud in 2026
Three real fraud mechanics we catch at the structural PDF layer.
Doctored proof of address
Name or address fields replaced on a real utility bill to establish false residency. Structural forensics detects the substitution.
Fabricated bank reference letter
A PDF mimicking a bank letter, produced through an editor. Producer signatures, font subsets, and object layout expose the forgery.
Altered corporate documents
Certificates of incorporation, shareholder registers, or source-of-funds letters edited to hide ownership or inflate financial standing.
The scale of the problem
The verification gap
KYC platforms verify the document. HTPBE verifies the file.
Two different checks — both matter.
Persona, Onfido, Alloy, Jumio, and Sumsub verify identity — face match, ID authenticity, liveness. They’re the right tool for the identity layer. They don’t analyze the structural integrity of supplementary PDFs (proof of address, bank letter, shareholder register). HTPBE sits next to those platforms as the structural-PDF layer they don’t provide.
Five forensic layers, one deterministic verdict
Every PDF we receive passes through the same structural pipeline — no model training, no thresholds to tune.
Metadata analysis
Creation and modification timestamps, producer and creator fields, XMP metadata — the first layer exposes basic tampering.
File structure
Xref tables, trailer chain, incremental updates. Any edit after export leaves a structural fingerprint here.
Digital signatures
Signature chain integrity and post-signature modifications produce deterministic markers. Certainty-level signal.
Content integrity
Fonts, objects, embedded content, page assembly. Multi-session edits and inserted objects are visible at this layer.
Verdict with markers
Deterministic output: INTACT / MODIFIED / INCONCLUSIVE, with named markers for every finding — suitable for audit trail.
PDF document types we verify for kyc & onboarding
Every type listed below is analyzed at the structural file layer — not the rendered image.
Detection capabilities
Deterministic structural signals. No probabilistic scores, no model training.
Incremental update detection
Any post-issuance edit leaves a fingerprint in the xref and trailer chain.
Producer signature validation
Real bank and government exports produce recognizable signatures. Edits and forgeries don’t match.
Font subset prefix consistency
Multi-session edits create detectable font subset shifts across pages.
Text layer vs. raster mismatch
Replaced text in rendered images breaks agreement between the text and visual layers.
Signature verification
Digitally signed documents are validated for post-signature modifications.
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
Frequently asked questions
No. Those platforms verify identity — face, ID, liveness. HTPBE verifies the PDFs an applicant uploads alongside their ID. They complement each other. Use the IDV platform for the person, HTPBE for the paperwork.
Yes. EDD typically involves more supporting documents — corporate structure, source of funds, UBO declarations. Each is a PDF that can be edited. HTPBE provides a structural-integrity check and an audit record for each.
Documents are processed through the API and the analysis response is returned to your system. Review the privacy and security documentation at /legal for specific handling details and request a DPA if you need one.
Structural analysis works best on digitally issued PDFs. Scans and photos are raster; our method has less to work with on pure rasters. Require digital PDF uploads where possible, or pair HTPBE with image-forensics tooling for raster-heavy flows.
Related solutions and guides
Alternative Lending
Document-integrity layer for loan applications alongside Plaid-style verification.
Mortgage Underwriting
Structural forensics for income and asset documents in mortgage origination.
Document Fraud Detection API
Technical overview of the HTPBE fraud detection API.
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.