●Financial services · Banks, lenders & insurers

Catch forged documents and deepfake customers.

Screen bank statements, invoices and IDs for edits and generation, and selfies for face swaps, inside your onboarding and lending flows.

Multi-model detection<3s per imageZero retention
bank_statement_0731.pdfscan complete
Submitted evidence
AI-generated
0.92LIKELIHOOD
Refer to review
Text re-render
92
PDF edit history
87
Font consistency
80
Template match
55
<3sMedian result time
4Independent signal families
0Files retained
C2PAProvenance read

●Platform

Detect it. Explain it. Act on it.

Every scan returns the same three things: a result, the signals that produced it, and a decision you can route on.

bank_statement_0731.pdfintake · 10:42:08
AI-generated
bank_statement_732.pdfintake · 10:42:11
Real
bank_statement_733.pdfintake · 10:42:15
AI-generated

01

Detect

Every file is scanned by independent models for images, video and faces, in the web tool, the extension or by API.

Text re-render
92
PDF edit history
87
Font consistency
80
Template match
55

3 / 4 signals corroborateCalibrated likelihood

02

Explain

See which signals fired and how strongly. No single model decides; every result comes with its reasons.

Approve
Review
Decline

Rule: likelihood ≥ 0.85 → Review<3s

03

Route

Branch your workflow on the result. Clean items pass, flags go to review with a full audit trail.

●The problem

Paper is easy to fake now.

Generative tools produce convincing statements, invoices and IDs. Edited PDFs pass a quick look. Deepfake selfies pass basic liveness.

StatementsEdited amounts and balances
InvoicesGenerated from scratch
IDsPhoto swaps and generated documents
SelfiesFace swaps in liveness checks

●What we catch

What gets flagged.

Flagged at the point of submission, before it reaches a reviewer.

01

Edited bank statements

Balances, dates and names changed.

02

Fake invoices

Fully generated or edited invoices.

03

Forged IDs

Generated documents and swapped photos.

04

Deepfake selfies

Face swaps in KYC video.

05

Fake screenshots

Payment confirmations and bank app screens.

06

Cloned voices

Callers authorising transfers. Coming soon.

The pipeline

A detector for each kind of media.

Image, video and voice each have their own detector. Their findings come back as one clear answer you can act on.

Image

Diffusion, GAN and face-swap images from Midjourney, DALL·E, Stable Diffusion, Flux and Firefly.

Live

Video

Face swaps across 32 frames and fully generated video from Runway, Kling, Veo and Pika.

Live

Voice

Cloned and synthesised speech in calls, notes and recordings.

Live

What you get

Each file is marked Approve, Review or Decline, with the likelihood, signals and audit ID behind it.

One answer

●Where it fits

Across the customer journey.

IDs and selfies at account opening.

Statements and invoices at underwriting.

Documents and photos at intake.

Screenshots in disputes and chargebacks.

Synthetic callers. Coming soon.

●How it works

Three steps. One result.

01

Submit

Documents, images or video by API, batch or upload.

02

Analyse

Text, layout, metadata, face and provenance checks.

03

Route

Approve, review or decline with an audit ID.

●Integration

Three ways in.
Start with the web app.

Scan in the web app or Chrome extension today. The REST API and MCP server for your AI agents are coming soon. Same detectors, same result, same audit trail.

Web app

Available

Upload in the web app. Images, video and voice, up to 50 MB. Full results in seconds.

witness.vision/scan
Page media● Scan
bank_statement_0731.pdf · AI-generated · 0.92

Chrome extension

Available

Scan any image or video from inside the tools your team already uses. No download, no upload.

portal.example.com
Page media● Scan
bank_statement_0731.pdf · AI-generated · 0.92

API

Soon

Single scans, batch jobs and webhooks. Structured JSON with result, likelihood, signals and audit ID.

POST /v1/detect
curl -X POST https://witness.vision/api/v1/detect \
  -H "Authorization: Bearer $WITNESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{"media_url": "https://…/bank_statement_0731.pdf"}'

→ 200 OK · 412ms
result: ai_generated · 0.92

●Why Witness

Built to be checked.

We say what the system does, what it returns and where its limits are.

Specialized models

Detection built per signal

Specialized models per signal, so you get more coverage and fewer false positives than one classifier.

Explainable

Reasons, not just a score

Every result shows the signals behind it and where in the file they fired.

Zero retention

Analysed, then gone

Media is never stored, shared or used for training.

C2PA

Provenance, when it exists

Reads Content Credentials from capture device to current file.

●Pricing

Priced around your volume.

No minimums and no long-term contracts. Tell us your volume and we will quote within one business day.

Free

$0

  • 20 image scans a month
  • 2 min video/voice total
  • Full heatmaps
  • Generator attribution
  • EXIF/C2PA/SynthID
  • Web and Chrome extension
Create free account

●Pro

$15 / month

  • 1,000 image scans a month
  • 10 min video/voice total
  • Everything in Free
  • Faces and face-swap specialist
  • API and MCP access (500 calls/mo)
  • PDF and CSV export
  • Cloud scan history
  • Email support
Get started →

Enterprise

Custom

  • Volume pricing
  • Everything in Pro
  • SSO and audit logs
  • Dedicated support
  • Custom SLA
  • On-premise option
Talk to sales

●FAQ

Common questions.

Something else? Talk to our team

Does it replace KYC vendors?

No. It adds a media authenticity layer to your existing stack.

Is there an audit trail?

Every result returns an audit ID and a forensic PDF is available.

Is data stored?

No. Files are analysed and discarded.