Candidate invited → Documents and consent → Selfie or video capture → Record checks → Report to employer
The face check confirms similarity and presence. It does not confirm the face is unmanipulated.
Background verification / NeuroVerify
Deepfake Detection API for Background Verification Platforms
Background verification providers vouch that a candidate is who they say they are. NeuroVerify checks the candidate selfie or video for deepfakes and face manipulation beyond liveness, and returns one risk score with signal-level evidence you can add to your report.
It runs on the selfie or video your portal, app or messaging flow already captures, so candidates take no extra step and you make one API call.
NeuroVerify does not run criminal, education, employment or address checks and does not verify documents. Your existing checks and your clients' hiring policies stay in place.
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
A verified report is only as good as the face behind it.
Background verification combines several checks: identity documents, address, criminal and court records, education and employment history. A selfie or video links the candidate to those records and often proves that the person who started the process is the person who finished it.
Remote hiring has made that link a target. A candidate, or someone working for them, can use a face-swap or generated video so that another person answers the check, passes face match and completes the verification. The report then states that a named person was verified when the face on camera belonged to someone else.
Why it matters to your product
Your customers rely on the report in hiring decisions. If the identity link is weak, every other check in the report is weakened. Cases of synthetic candidates and proxy interviews are increasingly discussed; see synthetic employee hiring fraud and the risk of onboarding a deepfake job candidate.
Threats
Attacks on candidate verification
These are attack patterns, not claims about any specific provider or employer.
01
Proxy candidate on a verification video
Another person completes the video check while a face-swap shows the real candidate's face.
02
Generated face for a fabricated candidate
A synthetic identity with assembled records and a generated face passes face match.
03
Virtual camera in the web portal
A pre-made clip replaces the live camera during candidate capture.
04
Re-verification by a different person
After hire, a different individual uses manipulated media to pass a periodic recheck.
05
Identity mismatch hidden by edited selfies
A face is altered to look like the document photo without being the document owner.
06
Bulk fraud through reused faces
One operator submits many applications with a limited set of re-rendered faces.
Where NeuroVerify fits
Add an authenticity result to your verification report
NeuroVerify sits after candidate capture in your product. Your portal, mobile SDK or messaging flow stays as it is. The result can be shown in your dashboard or included in the report alongside your own checks.
Documents and consent → Selfie or video → NeuroVerify risk score → Record checks → Report with authenticity evidence
One added call. The candidate experience is unchanged.
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 the documents your platform collects.
Backend SDKs for Python, TypeScript/Node.js, Go and Java and a REST API suit a platform product, and mobile SDKs cover candidate apps. See NeuroVerify.
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 candidate selfie or video
Pass the media your portal or app already captures for each candidate.
Read the unified risk score
Receive one score and signal-level evidence for the face in the media.
Surface it in your product
Show the result in your dashboard or report, with your own wording and thresholds.
Retain evidence per candidate
Store the result with the case so a client query can be answered later.
What you get
What it means for a verification provider
A stronger identity link in every report
Your report can say more than "face matched".
A feature your clients can see
Authenticity evidence becomes part of what you sell.
Fewer proxy and synthetic candidates
Manipulated media is flagged before the report is issued.
Reviewable, explainable decisions
Signal-level evidence helps analysts handle exceptions.
One integration across channels
Web, mobile and messaging flows share the same API.
Questions
What teams ask before they integrate.
Can we white-label the result inside our own report?
The result is returned as data in the API response, so you decide how it is presented in your dashboard or report. Talk to us about commercial and branding terms for platform use.
Does it verify the documents candidates upload?
No. NeuroVerify analyses face images, video and audio. It protects the selfie and video step that sits beside your document, record and database checks, and it does not replace any of them.
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 candidate selfie images, video and audio 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 candidate verification 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
Make your reports harder to fake.
Run NeuroVerify on candidate selfies and videos from your own platform and see what it adds to a report. Contact us to plan an evaluation.