Fake Experience Letter Detection — Catch Forged Proof
A fabricated experience letter looks identical to a real one — until you read the file structure. Talent ops teams, BGV operators, and visa sponsors all face the same pattern: a candidate cannot prove four years at a previous employer, so they author a letter in Microsoft Word, sign it themselves, export to PDF, upload. Visual review passes. Structural analysis does not.
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 fabricated or tampered experience letter, we’re the most specific tool for it.
When htpbe? returns INCONCLUSIVE on an experience letter, that’s the expected baseline (these documents legitimately come from desktop tools at small employers); combine with other markers before flagging.
One REST call, one deterministic verdict
Upload the PDF. The API returns INTACT, MODIFIED, or INCONCLUSIVE with named markers — in about three seconds.
How fake and tampered experience letters actually look
Three real fraud mechanics we catch at the structural PDF layer.
Letter authored in Microsoft Word from scratch
No previous employer involved. The candidate writes the letter in Word using the company’s logo lifted from LinkedIn, signs the HR Manager’s name, exports to PDF. The producer field shows Microsoft Word — not the document management system or CRM authentic letters come from.
Real letter with edited dates or salary
An applicant has a genuine letter from a brief stint, but the dates or compensation don’t support the role they’re applying for. They open the PDF in Adobe Acrobat or an online editor, change the dates from "Jan 2022 — Aug 2022" to "Jan 2020 — Aug 2024", re-export. Incremental update markers expose the edit.
Signature lifted and pasted
A signature image cropped from another document and pasted onto a fabricated letter. Image-layer artefacts (mismatched compression, misaligned baseline, redundant object streams) flag the substitution.
The scale
Why your existing checks miss this
BGV calls the employer. It does not inspect the file.
Both layers matter. The employer call only works if they pick up.
BGV platforms (AuthBridge, IDfy, OnGrid, Springworks) call the previous employer to confirm employment dates and role. This works when the employer responds — but Indian BGV failure rates on previous-employment verification routinely run 15–30% (employer non-response, defunct companies, HR-team turnover). When verification cannot be completed, candidates fill the gap with a letter. htpbe? catches the file the candidate sent, regardless of whether the previous employer responds. Use both: BGV for the fact when reachable, htpbe? for the file always.
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.
Experience letter and adjacent employment-proof PDFs we check
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.
Producer signature on the letter
Authentic experience letters come from the previous employer’s document workflow — typically a payroll engine, HRMS export, or DocuSign workflow. When the producer field shows Microsoft Word, LibreOffice, Google Docs, or Chrome Headless, the letter was authored on a desktop and exported by hand.
Letterhead consistency
Real corporate letterheads are embedded as part of the template’s font and image objects. Lifted-and-pasted logos appear as redundant image streams with mismatched compression — a structural fingerprint of fabrication.
Digital signature presence and chain
Many large employers digitally sign experience letters via DocuSign, Adobe Sign, or HelloSign. Authentic letters carry a valid signature chain. Fabricated letters either lack signatures entirely or have invalidated chains.
Incremental update trail
A clean export from a corporate document system has one xref table. Hand-edited letters have two or more — visible structural evidence of post-issuance editing.
Image-layer artefacts in pasted signatures
Signatures dropped in from external sources have different JPEG/PNG compression characteristics than the rest of the document. The image stream metadata exposes the paste.
Modification timestamp gap
Real letters have ModDate equal or near CreationDate. Hand-edited letters show gaps of days or weeks between creation and modification.
Two HTTP calls to verify any experience letter
Buyers can skip this section — developers, the integration is two HTTP calls.
Step 1 — submit the PDF
curl -X POST https://api.htpbe.tech/v1/analyze \
-H "Authorization: Bearer $HTPBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://your-storage/candidate-experience-letter.pdf"}'Step 2 — read the verdict
{
"id": "x1y2z3a4-5b6c-7d8e-9f0g-h1i2j3k4l5m6",
"status": "inconclusive",
"modification_confidence": "none",
"modification_markers": [
"Desktop-tool producer (Microsoft Word) — no corporate workflow signature",
"Single-session creation — no incremental update trail",
"No digital signature chain to verify"
],
"producer": "Microsoft Word",
"creator": "Microsoft Word",
"creation_date": 1707091200,
"modification_date": 1707091200,
"has_digital_signature": false,
"xref_count": 1,
"has_incremental_updates": false
}htpbe? returns inconclusive — there is no edit trail to confirm tampering, but the file lacks the corporate-workflow metadata real letters carry. In the experience-letter context, inconclusive is itself a high-confidence fraud signal: a genuine letter from a mid-size or large employer would carry a producer signature from their HRMS, e-sign workflow, or document management system — not Microsoft Word on a desktop. Treat inconclusive on an experience letter as a flag for manual employer verification.
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
inconclusive — a prompt for manual employer verification rather than an automatic reject.modified with the incremental-update marker — and your reviewer can see the file was changed after issuance.Related solutions and guides
HR & Hiring
Pre-employment document fraud detection for talent ops and BGV operators.
Fake Relieving Letter Detection
Sister page — same structural forensics applied to relieving letters at separation.
Fake Salary Slip Detection
Same forensics for monthly salary slips submitted as previous-employment proof.
Fake Offer Letter Detection
Same cluster — offer letter forensics for BGV, lending, and visa workflows.
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.