Fake receipt and screenshot detection for payments and disputes

Yes. Screenshots of transfers, balances and conversations are checked for edited regions, text that doesn’t match the surrounding rendering, and generation traces, with each finding marked where it sits. Screenshots carry little metadata, so the check rests mainly on the pixels and the text itself.

Yes. Receipts and invoices are checked for changed dates, amounts and line items, font and spacing that don’t match the rest of the document, rebuilt templates, and metadata that conflicts with the claimed source, such as a receipt last saved by an image editor. Each finding is marked on the page with its strength.

Photos submitted as proof of delivery, non-delivery or damage are checked for edits, AI generation and missing or conflicting camera data. A photo that was already used in another dispute is a separate question; comparing files across cases is in development.

Through the API or the Trustable web app. Send the receipt, screenshot, photo or statement attached to a dispute and get back the findings, where they are and how strong each one is. Routing results into your case tool is in development.

No. A flag means a file needs a closer look. Screenshots are cropped and annotated for innocent reasons, and that can look like editing. Trustable shows what it found and how strong the signal is; your agent decides whether to ask for more evidence or resolve the case.