Insurance fraud prevention: claims and onboarding
Pay genuine claims fast and investigate the fabricated ones. Your claims desk now receives evidence that anyone can generate, from policies bought and changed on phones you never see.
Hold
HOLD · device shared · document tampered · payout account shared- Your customer sees
- Your claim is with a claims handler, who will contact you before anything is paid.
- Your FRM receives
- SHARED_DEVICEDOC_TAMPEREDACCOUNT_SHARED
What insurers face now.
- Photos, documents and video submitted with claims can now be generated or edited.
- Policies are bought and changed remotely, on devices insurers never see.
- Deepfakes are one in five biometric fraud attempts. (Entrust (2026 Identity Fraud Report: deepfakes, social engineering and injection attacks on the rise, opens in a new tab), Nov 2025)
Across the customer journey.
Where each attack appears for insurers, what DeepID reads at that moment and the action it returns. Each moment is checked against what the one before it bound.
| Moment | The attack | What DeepID does | Decision |
|---|---|---|---|
| Policy onboarding | Fake or borrowed identities | A live face on a real camera, matched to the ID, with the device read below the camera. | Block |
| Claims intake | Edited bills, generated photos and prepared video | Supporting documents checked for edits, the capture path read at upload, and one device behind many claims. | Allow, or hold |
| Self-inspection | Replayed or injected video | Liveness on the inspection video catches an injected stream; a doubtful capture is filmed again in a guided step. | Step up |
| Payout | Payment to a ring account | The payout account verified against the name on it and linked to other claimants on the graph. | Hold |
Where to start.
The journey most at risk: a claim backed by photo or video evidence. Start at policy onboarding, where identity, liveness and the payout account are bound. Claim evidence is then checked on the same capture path, with the same document checks.
- 1Sign-upIdentity, a live face and the payout account, verified and bound.
- 2Claims deepfakesThe capture path, the device and the payout account behind a claim.
- 3Account takeoverA payout account change treated as a new-phone event.
- 4Video KYC deepfakesRemote onboarding, with the camera read below the picture.
Your free first analysis.
A free retrospective on a sample of closed claims, with their media, devices and payout accounts.
What it shows. The paid claims that shared a device, a repairer or a payout account with another claim, and the documents that carried edits. No figure is published for this; you count it on your own data, against what you see today.
Use cases for insurers.
Each shows how the attack unfolds, what your checks saw at each step, what DeepID read and the decision it returned.
Claims deepfakes
Pay clean claims without an extra step, and hold the fabricated ones.Hold, or allowVideo KYC deepfakes
A live person, in front of a real camera, on every video KYC call.Step up, hold or blockAccount takeover
Protect the account through recovery and the hours after.Step up, then cool offVulnerable customers
Extra time, and a call back, for the customers most at risk.Cool off, then holdInsider fraud
Hold the takeover that starts with a contact change made from the inside.Step up, then hold
The modules these use cases read with.
Open a module to see what it reads and the reasons it sends with each decision.
See DeepID on a real phone.
We show your fraud, security and engineering leads how DeepID would run your sign-up, login or payment journey, then plan a pilot on your own traffic.