Document fraud detection

Detect a fake expense report

Till receipts, restaurant bills, taxi receipts: expense report documents are numerous, low in value and rarely checked one by one. That is exactly what makes them an easy target. Docusan analyzes every receipt to flag those that deserve a closer look.

Typical frauds

The most common forgeries

01

Edited amount

The total of a receipt or invoice is retouched to obtain a higher refund.

02

AI-generated receipt

Artificial intelligence tools can now produce a realistic photo of a till receipt in seconds.

03

Recomposed receipt

Elements from several receipts are combined to create an expense that never happened.

Our detection approach

What Docusan analyzes

Four levels of analysis to spot forgeries, whether the document is a PDF, a scan or a photo.

01

Metadata

  • Missing metadata
  • Inconsistencies in the file properties
02

Pixel-level anomalies

  • AI-generated images, deepfakes
  • Inserted content (splicing, inpainting, copy-move…)
03

Structural anomalies

  • Edits and annotations
  • Recovery of previous versions
04

Customizable detectors

  • Consistency with document templates
  • Data cross-checking
  • Watchlists

Relevant industries

FAQ

Your questions

Are AI-generated receipts detected?

Yes. Docusan identifies images generated by artificial intelligence. The result is a risk level for your teams to interpret.

Can Docusan integrate with our expense management tool?

Yes. The API sends each receipt to Docusan automatically and returns its risk level to your tool in real time.

Should every receipt be checked?

That is the whole point of automatic analysis: each receipt is examined in seconds, and your teams focus on the flagged ones.

Free trial

Test Docusan on your own documents

Upload a PDF, scan or photo and get a verdict within seconds.