Looking for a Veryfi alternative for PDF integrity? — Different category by design
AP and expense-ops teams know Veryfi for OCR extraction and data structuring on receipts and invoices. htpbe? answers a different question: was the PDF itself modified or fabricated? We don't extract data — we read the structural layer (producer, xref, signatures, image streams) and report INTACT, MODIFIED, or INCONCLUSIVE. Pair us with Veryfi (or any OCR layer) for a complete pipeline, or use standalone if structural fraud is your specific gap.
htpbe? is not an OCR replacement. We don't extract amounts, dates, vendor names, or line items — that's what Veryfi and similar platforms (AWS Textract, Google Document AI) are for. We answer "did this PDF get modified or fabricated after issuance?" — a structural-forensics question that's orthogonal to extraction.
One REST call, one deterministic verdict
Upload the PDF. The API returns INTACT, MODIFIED, or INCONCLUSIVE with named markers — in about three seconds.
Why teams use htpbe? alongside Veryfi (not instead of)
Three real fraud mechanics we catch at the structural PDF layer.
OCR + structural forensics is the right pipeline
Veryfi extracts the data (vendor name, amounts, line items). htpbe? answers whether the underlying PDF was edited. Both pieces of information are useful — extraction tells you what the document says, structural forensics tells you whether you can trust it. Most AP fraud-ops pipelines benefit from both.
Self-serve, public pricing
Plans from $15/mo (30 requests) to $499/mo (1,500 requests) with public pricing. Sign up, get an API key, ship the integration the same day. Free test keys on every plan.
Structural-only depth
htpbe? focuses on one thing: PDF integrity. That focus shows up in detection depth — incremental update, signature chain, ghost-info scan, font subset divergence, balance arithmetic, image-stream artefacts. Across 10 forensic layers, dedicated to PDF structural fraud.
How htpbe? is positioned
When htpbe? makes sense (and when Veryfi is the right tool)
Need data extraction? Veryfi. Need integrity check? htpbe? Best practice: both.
They're complementary, not competing.
Veryfi is built for OCR extraction — turning a receipt or invoice PDF into structured data your accounting system can consume. htpbe? is built for integrity checking — verifying the PDF wasn't modified or fabricated. Most AP and expense-ops pipelines that take fraud seriously use both: Veryfi (or a similar OCR engine) for extraction, htpbe? for structural integrity. Picking one over the other typically means the gap shows up later. The honest answer is "use both for full coverage" rather than "switch from Veryfi to htpbe?".
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.
PDFs we analyze structurally for AP and expense ops
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 analysis
Authentic invoices come from accounting software (QuickBooks, Xero, SAP, NetSuite, Zoho). Authentic receipts come from POS systems. When the producer field shows a desktop tool or generator-tool fingerprint (Microsoft Word, Chrome Headless, Puppeteer), htpbe? flags it.
Incremental update detection
Edits to a real invoice or receipt (changed amounts, vendor names, bank-account numbers) leave incremental update markers in the xref chain. Critical signal for BEC fraud and AP-line-item manipulation.
Digital signature chain validation
Many vendor invoices and structured receipts carry digital signatures. htpbe? validates the chain and flags invalidated or removed signatures — orthogonal to whatever Veryfi extracts.
Image-stream artefact detection
Lifted-and-pasted vendor logos and merchant headers leave compression artefacts that differ from authentic embedded content — a structural fingerprint of fabrication.
AI-rendered receipt detection
AI tools produce receipts through Chrome Headless, Puppeteer, wkhtmltopdf, or ReportLab toolchains. The producer field exposes the rendering pipeline, even when the visual layout looks pixel-perfect. INCONCLUSIVE on a "POS receipt" with a headless-browser producer is a strong fraud signal.
Cross-document fingerprint analysis
When multiple "different" vendor invoices share font subset prefixes, image hashes, or producer signatures across an expense submission, the API surfaces the shared fingerprints — useful for catching expense-fraud rings.
How htpbe? complements Veryfi (or any OCR layer)
Buyers can skip this section — developers, the integration is two HTTP calls.
Step 1 — submit the PDF (alongside or after your OCR step)
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/vendor-invoice.pdf"}'Step 2 — read the integrity verdict (independent of OCR)
{
"id": "v1e2r3y4-5f6i-7p8d-9z0f-a1b2c3d4e5f6",
"status": "modified",
"modification_confidence": "high",
"modification_markers": [
"Two cross-reference tables — incremental update",
"Modification date 6 days after creation date",
"PDF editor producer detected"
],
"producer": "Adobe Acrobat Pro",
"creator": "QuickBooks Online",
"creation_date": 1707091200,
"modification_date": 1707609600,
"has_digital_signature": false,
"xref_count": 2,
"has_incremental_updates": true
}Original came from QuickBooks Online — institutional accounting software. 6 days later it was opened in Adobe Acrobat Pro and re-saved, adding a second xref. Verdict: modified at high confidence. Pair this verdict with whatever Veryfi extracted — extraction tells you the bank-account number on the invoice, integrity tells you whether you can trust that the bank-account wasn't swapped after issuance (a classic BEC pattern).
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
Related solutions and guides
Accounts Payable
AP-vertical positioning — invoice fraud detection for finance ops.
Expense Reimbursement
Expense-ops vertical — receipt and reimbursement fraud detection.
Fake Receipt Detection
Receipt-specific structural forensics including AI-rendered detection.
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.