Recipient opens app or visits an agent → Face capture → Match to record → Certificate accepted → Payments continue
The match confirms similarity to the stored record. It does not confirm that the face is a living, real person.
Pensions and benefits / NeuroVerify
Deepfake Detection API for Digital Life Certificates
Pension funds and benefit agencies increasingly confirm that recipients are alive through a remote face capture. NeuroVerify checks that capture for deepfakes and manipulation beyond liveness, and returns one risk score with signal-level evidence before payments continue.
It runs on the face capture your digital proof-of-life flow already collects, so the recipient takes no extra step and you make one API call.
NeuroVerify does not confirm eligibility, identity records or payment entitlement, and it does not make the payment decision. Your programme rules and disbursing policy keep those decisions.
Powered byNeuroVerifyExplore the product
- #1 of 36on the public VendorBench-100
- <200 msp95 on eligible image requests
- 6 → 1six checks, one unified score
- 0new steps for your customer
The gap
Remote proof of life must tell a living person from a fabricated one.
Pension and benefit programmes pay recipients for as long as they live. Traditionally, recipients appear in person or submit a certificate each year. Many programmes now accept a remote check: a face capture on a phone, sometimes assisted by a bank, post office or service centre. India's Jeevan Pramaan is one example of this model; the same need exists in many countries.
The remote check creates an opening. If a recipient has died, someone may try to keep the payments flowing. A face-swap, a generated video or an altered photo of the deceased can be used to answer the capture. Recipients who are frail may also be impersonated by a relative or an agent.
What makes this use case different
Recipients are often older and less familiar with technology, so friction must stay low. Agents or relatives frequently help. Errors cost twice: a false accept pays someone who should not be paid, and a false reject stops a genuine pensioner's income. Evidence that a reviewer can read matters more here than in most flows. See synthetic media controls for government enrollment.
Threats
Attacks on remote proof of life
These are attack patterns, not claims about any specific programme.
01
Continuing payments after a recipient has died
Someone presents a generated or altered face to keep a deceased person's pension active.
02
Face-swap during an assisted capture
An agent or relative masks the real person on camera with the recipient's face.
03
Replay of an earlier genuine capture
A previous real recording or photo is replayed through the app to satisfy the check.
04
Synthetic recipients on benefit rolls
A fabricated beneficiary with a generated face is added and maintained.
05
Virtual camera on a shared device
Software feeds a prepared clip into the capture step on a helper's device.
06
Batch fraud by an assisted-channel operator
One operator submits many captures using re-rendered faces for multiple recipients.
Where NeuroVerify fits
Authenticity evidence before payments continue
NeuroVerify sits right after the face capture in your proof-of-life flow and before the certificate is accepted. The recipient, the assisting agent and your records match step all stay as they are.
Face capture → NeuroVerify risk score → Match to record → Certificate accepted, reviewed or held
One added call. The recipient takes the same capture as before.
Six signals run in one request: Visual Safety Screening, Live Presence Verification, Face Manipulation Detection, AI Generative Model Analysis, AI Pixel-Level Manipulation and AI Content Compliance. NeuroVerify analyses face images, video and audio. It does not analyse identity documents.
Government and public-sector programmes that need data kept inside their own boundary can deploy in a private cloud, on-premises or air-gapped. See government and deployment.
NeuroVerify Unified Trust LayerSix parallel analysis layers
- Visual Safety Screening
- Live Presence Verification
- Face Manipulation Detection
- AI Generative Model Analysis
- AI Pixel-Level Manipulation
- AI Content Compliance
Send the proof-of-life face capture
Pass the image or video your app or agent device already records.
Read the unified risk score
Receive one score with signal-level evidence in the response.
Accept, review or hold under programme policy
Send high-risk captures to a human case worker and never cut off a genuine recipient automatically.
Retain the evidence with the case
Keep the result for audits, appeals and disbursing-agency review.
What you get
What it means for pension and benefit programmes
Fewer payments to deceased or fake recipients
Manipulated captures are flagged before a certificate is accepted.
Protects genuine recipients
Evidence supports a human review rather than an automatic rejection.
Works for assisted and self-service capture
The same call covers phones, agent devices and service-centre captures.
Readable evidence for case workers
Signal-level results explain why a capture was flagged.
Keeps data in your boundary
Private cloud, on-premises and air-gapped options for public-sector rules.
Questions
What teams ask before they integrate.
Is this only for India's Jeevan Pramaan?
No. Jeevan Pramaan is one example of digital proof of life. NeuroVerify applies to any programme in any country that confirms a recipient is alive with a face capture, whether through an app, an agent device or a service centre.
How do we avoid wrongly rejecting a genuine pensioner?
Treat the score as evidence for a human reviewer, not as an automatic stop. Set a review band in your policy, route high scores to a case worker, and offer an alternative way to prove life, such as an in-person check. The decision always stays with your programme.
Do we still need a separate liveness check?
Not for this purpose. Live Presence Verification is one of the six signals NeuroVerify runs in a single request, alongside Face Manipulation Detection, AI Generative Model Analysis, AI Pixel-Level Manipulation, Visual Safety Screening and AI Content Compliance. It checks face images, video and audio from proof-of-life captures for deepfakes and manipulation beyond liveness.
If you already run a liveness vendor, keep it during evaluation and compare outcomes on your own media before deciding what to retire. The difference is explained in Deepfake Detection vs Liveness Detection.
How much work is the integration?
It fits the capture step you already run, so the end user sees nothing new. You send the media you already collect to one API call. Native mobile SDKs (Android/Kotlin, iOS/Swift, Flutter), backend SDKs (Python, TypeScript/Node.js, Go, Java) and a REST API are available, and an MCP server covers AI agents.
Two lines to integrate and live in under 24 hours are product claims. Your own timeline depends on how your proof-of-life flow is wired.
How fast is it, and will it slow the journey?
NeuroVerify returns in under 200 ms at p95 on eligible image requests under defined test conditions. The methodology is available on request. Video and audio take longer than a single image, so decide with your team which step runs inline and which runs in the background.
Where does the data go, and how can we deploy it?
You choose the deployment model: managed cloud API, private cloud or customer VPC, secure container, on-premises, or air-gapped. Neural Defend holds ISO/IEC 27001, ISO/IEC 27701, ISO/IEC 42001 and SOC 2 Type II certifications. Your legal team decides consent, retention and residency for the media you send.
Details are on the deployment and product data handling pages. For the privacy angle, see GDPR, Biometrics, and Authenticity Analysis.
Can we evaluate it on our own media?
Yes, and that is the test that matters. On the public VendorBench-100 benchmark, NeuroVerify ranked first of 36 systems with a detection score (MCC) of 0.876 against 0.646 for the next-best vendor. A benchmark does not reflect your devices, lighting, compression or attack mix, so bring representative samples from your own journey.
Contact us to set up an evaluation.
How do we handle false positives and set thresholds?
NeuroVerify returns one unified risk score with signal-level evidence. It does not approve or reject anyone. Your policy sets the thresholds and decides what happens at each level: continue, step up to a manual review, or decline.
The signal-level evidence tells a reviewer why a case scored high, which makes review queues faster and decisions easier to explain later.
Evaluate NeuroVerify
Test remote proof of life on your own captures.
Send face captures from your own programme and review the risk scores and evidence. Contact us to plan an evaluation.