Step 1 01
Scan
A user registers their palm with a quick scan on their own smartphone. Third-party apps either redirect to the Very app or use the Very SDK to create a native experience within their own app.
Real authentication, backed by over a decade of research.
Very is using proprietary, frontier palm biometrics to solve the internet's most urgent challenge: authenticating real users and AI agents to stop spam, fraud, and account takeovers.
A single palm scan. Four steps.
All Very products are built around our proprietary palm scan.
Step 2 02
Processing
The palm capture is converted into a mathematical Palm Model on the user's device. That model is then sent to an isolated, encrypted environment.
Step 3 03
Verify
The user is asked to verify their palm and prove liveness with a directed movement at key moments. This new Palm Model is then compared against the stored registration model.
Step 4 04
Output
Apps are only given a pass/fail state. This state can be applied to different actions within the app, gating access behind a proven verification.
Very is one of the only solutions to solve the verification trilemma.
Accuracy
Global precision from a single palm.
One of the fundamental measurements for biometrics is False Acceptance Rate: the likelihood of a result giving a false match for two different biometric signatures.
Very's single palm verification achieves a False Acceptance Rate (FAR) of 10-7, while Apple Face ID reaches a FAR of 10-6 — a 10× improvement, well above the industry average.
During registration, users scan each palm five times. These additional scans allow Very's FAR to further compound to 2.5 × 10-13. At this level, Very has the precision needed to distinguish individuals across a global population of eight billion and beyond.
10-7Single palm FAR — 1 in 10 million
2.5 × 10-13Dual palm FAR
Scalability
No additional hardware.
Very can be used on almost any modern smartphone without any additional hardware. Very's requirements cover 85% of the modern smartphone market.
Unlike other solutions, which require expensive or communally owned hardware, Very can run verifications at global scale. We regularly verify tens of thousands of palms daily.
85% of modern market coverage
Privacy
Designed to protect biometric data.
User privacy is a fundamental piece of our design architecture. The SDK derives a mathematical Palm Model from the palm capture. Biometric data is protected in transit and at rest, and enrolled Palm Models are stored in an isolated, encrypted environment.
In the standard integration, customer apps do not receive Palm Images or Palm Models; they receive a pseudonymous account identifier and limited verification metadata, such as the timestamp, result, and specifically authorized attributes.
Security
Preventing spoofs and stopping breaches.
Palms are more resistant to targeted attacks than other biometric platforms. They cannot be created wholesale from a digital footprint like facial recognition, and whole palm prints are rarely lifted in real life.
Very combines full palm scans with liveness detection, asking the user to complete randomized hand and finger motions in real time. This makes spoofing with an AI-generated palm image or video even more difficult.
Northwestern University
Human-AI Collaboration Lab
Fighting the deepfake arms race is of the utmost concern. That's why we team up with Northwestern University's Human-AI Collaboration Lab to make sure we're on the cutting edge of research and understanding.
How Very compares.
| Method | Accuracy | Security | Scalability | Privacy |
|---|---|---|---|---|
| Fingerprint | Medium | Medium: Can be lifted from touches | Low: Needs special hardware | Low: Linked to identification databases. |
| Face | Medium | Medium: Can be pulled from digital footprint | High | Low: Linked to identification databases |
| Iris | High | High | Low: Needs special hardware | Medium: Linked to identification databases |
| DNA | High | High | Low: Needs special hardware | Low: All biometric information |
| Very Palm | High: 10× more accurate than Face ID | High: Entire palm print rarely left behind. | High: Can be used on any modern smartphone. | High: Not linked to current identification databases. |
Compliance-ready.
VeryAI provides biometric authentication infrastructure rather than KYC decision-making and does not require government IDs for palm verification.
More Compliance and Trust SOC 2GDPRBIPADEA EPCS
Stop bots and clean up your platform in hours.
Get your API keys and access to the Very Dashboard.
Get started