Regulated onboarding · CySEC / EMI / PSP

Your KYC vendor said PASS.
Can you prove what it examined?

When AMLA or your supervisor asks what document your system actually verified, a vendor confidence score is not an answer. Plica gives you an independent forensic record — at the object level, before your pipeline touched the file.

What gets faked

The documents behind onboarding fraud.

ID / passport
AI-generated or face-swapped identity documents that pass basic OCR and template checks.
Proof of address
Synthetic utility bills assembled in software — perfect layout, no capture provenance.
Source of funds
Edited bank statements where balances or transactions were altered after export.
What breaks today

The detector sees a copy — not the original.

Between upload and analysis, your intake pipeline resizes, recompresses and strips metadata. The detector scores a derivative, not the file your client submitted. The forensic signals needed to prove authenticity may already be gone — and you cannot reconstruct what was examined. We call this Pipeline-Induced Provenance Loss.

How Plica solves it

Three steps to a defensible record.

01
Verify
Forensic check across container metadata, embedded pixels and provenance — one verdict with reason codes, not a black-box score.
02
Policy
Machine-readable action for your workflow: approve, hold for review, reject — calibrated to provenance quality, not task risk.
03
Evidence
A defensible packet tying the verdict to the original intake object. Reproducible when AMLA or CySEC asks, months later.
Insurance claims · damage & document fraud

The claim photo looks real.
Was it edited before you paid?

Claimants now edit damage photos and generate supporting documents with mobile AI tools. The adjuster sees a clean image; the payout goes out. Plica detects the manipulation a human eye and a standard detector miss.

What gets faked

The documents behind claims fraud.

Damage photos
Generative inpainting adds or removes damage — scratches, water, breakage — with no visible seam.
Utility / proof bills
AI-built utility bills used as proof of residence or ownership in a claim.
Invoices / receipts
Edited repair invoices where amounts or vendor details were altered after creation.
What breaks today

A clean-looking image is not a real one.

The fraudster controls the layer you look at — the pixels. What they cannot control is the layer beneath: sensor noise, container fingerprints, compression history. When a photo is edited, the physical signature breaks where the edit happened. The adjuster's eye misses it. The forensic layer does not.

How Plica solves it

Three steps to a confident payout decision.

01
Upload
Send claim photos and documents via API or email — JPEG, PNG, HEIC, PDF. No integration required to start.
02
Analyse
Multi-layer forensics: inpainting artifacts, PRNU break, GAN fingerprints, container and metadata anomalies.
03
Report
A human-readable report showing which signals fired and where — defensible if the claimant disputes the decision.
Car rental · vehicle return fraud

Return photos look clean.
Then you find the scratches.

Customers photograph the damaged car, edit out the scratches with a mobile AI app, and submit through your portal. You release the deposit on a manipulated photo. Plica checks the image before the money goes out.

What gets faked

The images behind deposit fraud.

Return photos
Scratches, dents and damage erased with Snapseed, Firefly, or built-in phone AI erasers.
Pre-rental photos
Damage added to "before" images to claim pre-existing condition that was not there.
Fuel / odometer
Dashboard photos edited to dispute fuel or mileage charges.
What breaks today

Editing is invisible to the eye — not to the sensor.

When pixels are replaced in an editor, the camera's continuous sensor noise (PRNU) breaks in the edited region. Compression history shifts. The edit is seamless to a person at the counter — but it leaves a structural trace the original capture never had. That trace is what Plica reads.

How Plica solves it

Three steps before you release the deposit.

01
Upload
Send return photos through the API or email — including any you suspect were manipulated.
02
Analyse
Forensic detection of inpainting, PRNU break, GAN texture and sterility — verdict in seconds.
03
Report
A clear verdict per photo — authentic, review, or manipulated — with evidence you can show the customer in a dispute.
Agentic AI · autonomous file decisions

Your agent reads the invoice.
Can it trust the file?

As AI agents process invoices, onboard vendors and trigger payments, the breaking point is no longer the payment rail — it is the object the agent trusted. Plica is the forensic layer that tells an agent whether a file can function as evidence before it acts.

What gets faked

The artifacts behind agentic fraud.

Invoices
Template-farm or AI-built invoices that an agent reads and routes for payment without witnessing.
Vendor documents
Synthetic KYB packs — certificates, registrations — submitted to onboard a fictitious vendor.
Tax / identity forms
Generated tax forms and IDs in a global contractor pool, across trust boundaries.
What breaks today

Reading a file is not the same as witnessing it.

Agent infrastructure is built for negotiation, extraction and spend. The forensic layer — the one that answers "can this file function as defensible evidence?" — is mostly absent. An agent that reads an invoice is useful. An agent that verifies the invoice is authentic before it pays closes the gap between automation and autonomy.

How Plica solves it

A machine-consumable trust outcome.

01
Verify
Forensic assessment at intake — metadata, container, sensor — before internal systems rewrite the object.
02
Decide
One enforceable outcome for the agent: proceed, escalate to human, or reject — with Forensic Reason Codes.
03
Record
An evidence packet that survives audit — what the agent saw, which version, what policy applied.

One layer. Every file-based decision.

Plugs into your stack — works alongside Sumsub, Onfido, Veriff. It does not replace them.

Try the API — free →
Plica · Independent Forensic Boutique · Larnaca, Cyprus  ·  [email protected]  ·  ← Back to home