Supported document type
Detect tampered and deepfake Closing Disclosure
A closing disclosure is the standardised statement of what a mortgage will cost, delivered to the borrower before closing. Its fixed layout and internal maths make it hard to alter unnoticed: the interest rate, the annual percentage rate, the projected payments, and the cash to close all have to agree. An APR lower than the note rate, or a cash-to-close figure that is not the sum of its lines, marks a document that was edited rather than generated.
API slug: closing_disclosure
What a genuine closing disclosure contains
The form runs to five pages. It sets out the loan terms (amount, rate, monthly principal and interest, and whether these can change), projected payments including taxes and insurance, and costs at closing. Later pages itemise loan costs and other costs, compute cash to close, and give the finance charge, total of payments, APR, and total interest percentage. The lender, settlement agent, and property details close the form.
Several relationships can be tested from the page. Cash to close equals total closing costs less lender credits plus the down payment and other adjustments. Monthly principal and interest follow from amount, rate, and term. For a closed-end loan the APR is at least the interest rate, because it folds in prepaid finance charges. The total interest percentage is total interest over the loan divided by the loan amount.
How closing disclosure forgeries are made
Rate and APR edits
The interest rate is lowered to improve affordability, or the APR is left unchanged after the rate moved. On a fixed-rate loan without a buydown, an APR below the stated rate is arithmetically impossible and a direct sign of alteration.
Cash to close adjustment
The funds required at closing are reduced to hide how much the borrower must bring. The itemised lines on the earlier pages then fail to sum to the printed figure.
Payment understatement
Projected monthly payment is trimmed to fit a debt-to-income limit. It stops matching the loan amount, rate, and term stated on the same page.
Mismatch with the loan estimate
Figures are changed on one document and not the other, or the disclosure is assembled from a template with different fee sections. Comparison between the two forms shows changes no lender would make.
What TamperCheck checks on a closing disclosure
TamperCheck runs 200+ forensic checks across three layers and returns a risk score from 0 to 100 with plain-English findings tied to specific regions of the document. These three carry the most weight on this document class.
Arithmetic reconciliation
Stated totals are recomputed from their components, and running or cumulative figures are checked for continuity across periods. A single edited value breaks the chain even when the page still looks right.
Table structure integrity
Inserted and deleted rows leave structural artifacts behind: inconsistent spacing, misaligned columns, and formatting the visible table no longer accounts for.
Field-level forensics
Every text region is analysed in its own right rather than as part of one whole-page image. This catches the smoothed and feathered edits that whole-image Error Level Analysis misses entirely.
And many more checks
The three above are the layers that carry the most weight on a closing disclosure. Every upload runs the full suite of 200+ checks regardless of document class, spanning file structure and metadata, pixel-level forensics, font and text rendering, optical and print characteristics, provenance signals, AI-generation signatures, and many more checks.
Who verifies a closing disclosure, and why
Mortgage underwriters, closing agents, and compliance reviewers. In each case the document is being used to unlock money, access, or a legal status, which is exactly what makes it worth forging.
How to verify a closing disclosure in 4 steps
Check the fields against each other
Read interest rate and APR, cash to close, and projected payments together rather than one at a time. Forgers typically change one value and leave the rest of the document describing the original.
Inspect the file metadata
Open the document properties and look at the producer, creation date, and modification date. A document produced by a consumer PDF editor, or created long after the date printed on its face, is worth a closer look.
Ask for a second document
Request a corroborating document from the same issuer or an adjacent period. Forgery effort concentrates on one file, so inconsistencies surface as soon as there are two to compare.
Run a forensic check
Manual review catches obvious edits but not field-level pixel manipulation or synthetic generation. TamperCheck runs 200+ forensic checks on a closing disclosure and returns a risk score from 0 to 100 in about a minute, at $0.50 per document.
Frequently asked questions
How do mortgage underwriters check a closing disclosure?
They compare it with the loan estimate and the approval, verify the arithmetic on cash to close and monthly payments, and confirm that the APR is consistent with the rate. Forensic review of the PDF tests whether numbers were altered after the form was generated.
What can be edited on a closing disclosure?
Most often the interest rate, monthly payment, cash to close, and the loan amount. Each has knock-on figures elsewhere on the form, so changing one without the others leaves detectable contradictions.
Can the APR be lower than the interest rate?
On a fixed-rate loan without a buydown, no. The APR takes the nominal rate and adds the effect of prepaid finance charges, which can only raise the figure. Adjustable-rate loans and temporary buydowns are the exceptions, because their APR is a composite of rates over the loan's life.
What is the difference between a loan estimate and a closing disclosure?
The loan estimate is the early, non-binding statement of expected terms and costs, given after application. The closing disclosure is the final statement, provided before closing. Both use standard layouts, and material differences between them should be explainable.
TamperCheck analyses closing disclosure uploads with a hybrid forensic and AI pipeline tuned for this document class. Upload endpoints accept PDF and common image formats; class is inferred automatically. See the API documentation for authentication, async jobs, and webhooks.