Seller verification / NeuroVerify
Seller onboarding ties a business to a real person: the proprietor or director takes a selfie that is matched to an ID. Scam sellers now use face swaps and generated faces to pass that check under a stolen or invented identity. NeuroVerify checks the selfie for deepfakes beyond liveness, in one API call.
It fits the seller verification step you already run: send the selfie or video you already capture, with no new step for the seller.
NeuroVerify does not verify business registrations, tax IDs or documents, and it does not decide who may sell. It adds authenticity evidence for the face media in your seller checks.
The gap
Seller verification usually has two halves. Business checks confirm a company or trading name exists. Identity checks confirm a person behind it: an ID document, a selfie and a liveness prompt, plus a face match. Together they decide whether payouts and listings are enabled.
Business registries and document checks say nothing about whether the selfie is genuine. A fraudster can register a real business using a stolen identity, and a deepfake selfie can make the proprietor appear present and matching.
Register business → Upload ID → Proprietor selfie and liveness → Face match → Payouts enabled
A passed selfie unlocks payouts. If it was a deepfake, the real owner of the identity is unaware and the marketplace carries the loss and reputational risk.
Sellers also change often: payout accounts, bank details and contact information. Each change is a chance to re-run the same selfie check. See Seller Identity Controls for Marketplace Onboarding.
Threats
These are attack techniques, not claims about any specific marketplace. Each targets the face evidence behind an approved seller.
The attacker holds a victim's ID and swaps the victim's face onto their own live video so the selfie matches the document.
A synthetic face is paired with a fabricated ID and business details to create a seller who never existed. See Synthetic Identity Fraud.
Prepared footage is injected in place of the live camera, so the app never sees the attacker. See Digital Injection Attacks.
A seller removed for fraud returns under a new identity, using edited or generated selfies that differ enough to avoid duplicate checks.
Once a genuine seller is approved, an attacker passes a selfie re-check with a deepfake of them and redirects payouts.
A verified account is passed to someone else who passes later step-up checks with a manipulated selfie.
Rules for seller verification differ by region and sector. Authenticity evidence supports your controls and your trust and safety policy decides what to approve. See FATF Digital Identity Guidance.
Where NeuroVerify fits
NeuroVerify sits after the proprietor selfie is captured and before your policy enables the account. Your business verification and ID checks stay in place.
Register → ID → Selfie and liveness → Face match → Payouts enabled
A face-swapped selfie that matches the ID is approved.
Register → ID → Selfie → NeuroVerify risk score → Face match → Payouts enabled or reviewed
One call is added. The seller sees no new step.
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. You get one unified risk score with signal-level evidence. See NeuroVerify.
Your business registry checks, ID verification, face match and approval decisions stay with you. NeuroVerify supplies authenticity evidence.
Pass the selfie or video from seller onboarding through a mobile SDK, a backend SDK or the REST API.
Receive one risk score with signal-level evidence, typically under 200 ms p95 for eligible image requests.
Use your own thresholds to enable the account, hold it for review or ask for a step-up.
Run the same call on payout detail changes or reinstatement of a suspended seller.
What you get
Face swaps and generated faces are caught beyond liveness, before payouts and listings are enabled.
Fewer stolen identities are used to open seller accounts without the owner knowing.
The same API protects payout changes and suspended-seller returns, not only first onboarding.
Signal-level evidence explains why a seller was held, which helps appeals and internal audit.
Sellers take the selfie they already take. Onboarding conversion is not asked to absorb a new step.
Two lines to integrate and live in under 24 hours, with SDKs for mobile and backend stacks.
Questions
No. It checks face images, video and audio for deepfakes and manipulation. Business registry checks and document verification stay with your existing providers.
Yes. Any step that captures a selfie or video can send it to the same API. Many teams add it to high-risk changes as well as first onboarding. Your policy sets which events trigger a check.
Liveness answers whether a live person appears to be present. It was not built to answer whether the face, video or audio was generated or manipulated. A face swap, a virtual camera feed or a synthetic video can still pass a liveness prompt.
NeuroVerify includes Live Presence Verification as one of six signals, then adds face manipulation, generative-model and pixel-level analysis in the same request. You keep your existing liveness step and add authenticity evidence to it. See Deepfake Detection vs Liveness Detection.
Most teams send the media they already capture. There is no new step for the end user. NeuroVerify offers native mobile SDKs (Android/Kotlin, iOS/Swift, Flutter), backend SDKs (Python, TypeScript/Node.js, Go, Java), a REST API and an MCP server for AI agents.
Integration is two lines of code, and teams can be live in under 24 hours. That is a product claim; your timeline depends on your own change process.
NeuroVerify targets under 200 ms p95 on eligible image requests, measured under defined test conditions. The test methodology is available on request, so you can compare it with your own latency budget.
Video and audio checks take longer than image checks. Share your media types during evaluation and we will confirm the expected timings.
NeuroVerify can run as a managed cloud API, in a private cloud or customer VPC, as a secure container, on-premises, or air-gapped. Pick the option that fits your security review and data-residency rules. See Deployment and Product data handling.
Neural Defend holds ISO/IEC 27001, ISO/IEC 27701, ISO/IEC 42001 and SOC 2 Type II certifications, shown on the Trust page.
You do. NeuroVerify returns one unified risk score with signal-level evidence. Your own policy decides what to approve, send to review or block. No detector is perfect, so set thresholds against your own risk appetite and review volume.
Because the evidence is signal-level, reviewers can see why a case was flagged instead of facing an unexplained score.
Evaluate NeuroVerify
Send us seller selfie and video media and see the unified risk score and signal-level evidence on your own captures.
