Detect tampered and deepfake Quotation

What a genuine quotation contains

Whatever the issuer or jurisdiction, a quotation carries a small set of load-bearing fields: unit prices and totals, quote validity date, quote number, and seller name and bank details. These are the fields a reviewer reads, and the fields a forger edits.

They are also bound to one another and to the file that carries them. Dates sit in a plausible order, identifiers follow the issuer's format, and every field was laid down in a single production pass, so they share one compression history, one font rendering, and one noise profile. A genuine document satisfies all of those relationships at once. An edited one rarely does.

How quotation forgeries are made

• Altering the unit prices and totals

  The unit prices and totals are overwritten in place while the surrounding page is left untouched. The document still reads correctly, but the edited region no longer shares the compression history and font rendering of the surrounding text, and any total derived from it stops reconciling.

• Altering the quote validity date

  Shifting the quote validity date makes an old or out-of-scope document read as current. This is the cheapest forgery to attempt, changing only a handful of characters, and the one most often missed by reviewers checking content rather than chronology.

• Altering the quote number

  Fabricating or transplanting the quote number defeats checks that only confirm an identifier is well-formed. A structurally valid value copied from a real document satisfies format validation while belonging to someone else entirely.

• Altering the seller name and bank details

  Substituting the seller name and bank details repurposes a genuine document so it describes a different person or organisation than the one it was issued to. Every other element is authentic, which is why visual review tends to pass it.

• Fully synthetic generation

  The whole document is produced by a generative model or an online template service rather than edited from a real source. Every field is internally consistent, so logical and arithmetic checks pass. These are caught by generation signatures instead.

• Print and rescan laundering

  The edited file is printed and then photographed or scanned to destroy the digital edit trail. This removes the original metadata, but resampling and reprinting introduce their own detectable artifacts.

What TamperCheck checks on a quotation

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.

• Letterhead, logo, and issuer plausibility

  Issuer branding is checked for resolution and compression consistency against the body text it sits on. A logo lifted from a website carries the signature of its source, not of the document.

• And many more checks

  The three above are the layers that carry the most weight on a quotation. 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 quotation, and why

Procurement and finance teams, lenders, and buyers comparing supplier quotes. 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 quotation in 4 steps

1. 1

   Check the fields against each other

   Read unit prices and totals, quote validity date, and quote number together rather than one at a time. Forgers typically change one value and leave the rest of the document describing the original.

2. 2

   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.

3. 3

   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.

4. 4

   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 quotation and returns a risk score from 0 to 100 within seconds, at $0.50 per document.

Frequently asked questions