Home/Documents/NRIC (Singapore National ID)

Supported document type

Detect tampered and deepfake NRIC (Singapore National ID)

The National Registration Identity Card (NRIC) is Singapore's compulsory identity document for citizens and permanent residents aged fifteen and above, issued by the Immigration and Checkpoints Authority, and it anchors KYC at banks, telcos, and government services. Its nine-character number carries a computed check letter, which makes fabricated numbers cheap to catch, and its citizen-versus-permanent-resident prefixes make status edits equally visible.

API slug: nric

What a genuine NRIC contains

The number reads as a letter, seven digits, and a check letter: S and T prefixes mark citizens by birth cohort, while F and G mark permanent residents, and the final letter is computed from the digits and the prefix. The front carries photograph, name, race, date of birth, sex, and country of birth; the reverse carries the registered address and a barcode.

Older pink and blue cards have given way to polycarbonate editions, and several designs circulate legitimately. Because the digits and the prefix together determine the final letter, a number that fails the computation was typed rather than issued, whatever the print quality around it.

How NRIC forgeries are made

  • Check-letter recomputation

    The final letter is a deterministic function of the prefix and digits. A number failing the computation was invented, which turns the NRIC number into one of the cheapest structural checks in identity verification.

  • Prefix and status coherence

    S and T prefixes mark citizens and F and G mark permanent residents, by cohort. A card claiming citizenship with a permanent-resident prefix, or the reverse, contradicts its own number.

  • Photograph and field patching

    Portrait swaps and address edits are the physical fraud. Cut-line edges, resolution steps, or font passes that change mid-field localise the substituted region.

  • Edition conformance

    Polycarbonate and earlier editions differ in layout and security features, and the analysis scores each against its own design. Mixing design elements across generations signals assembly rather than issue.

What TamperCheck checks on a NRIC

TamperCheck runs 200+ forensic checks across three layers and returns a risk score from 0 to 100 with plain-English findings tied to specific regions of the document. These three carry the most weight on this document class.

  • Portrait substitution and face-swap analysis

    The document is isolated from whatever it was photographed on, then the portrait region is assessed against the card surface around it. A pasted or generated face rarely matches the substrate it was placed onto.

  • Security print, foil, and hologram analysis

    A genuine security overlay or guilloche background behaves differently from a printed picture of one. A reproduction loses the structure that made the feature a security feature in the first place, and that loss is measurable even when the copy looks convincing on screen.

  • Reference and document number checks

    Document, account, and reference numbers are checked for issuer format conformance and against every other place the same value appears on the page.

  • And many more checks

    The three above are the layers that carry the most weight on a NRIC. Every upload runs the full suite of 200+ checks regardless of document class, spanning file structure and metadata, pixel-level forensics, font and text rendering, optical and print characteristics, provenance signals, AI-generation signatures, and many more checks.

Who verifies a NRIC, and why

Singapore banks, fintechs, and telcos. In each case the document is being used to unlock money, access, or a legal status, which is exactly what makes it worth forging.

How to verify a NRIC in 4 steps

  1. Photograph both sides

    Capture front and back flat at full resolution so the number, check letter, and address block survive close analysis.

  2. Validate the number

    Apply the check-letter computation over the prefix and digits. A failure marks a fabricated number regardless of print quality.

  3. Cross-check status and fields

    Confirm the prefix agrees with the citizenship status claimed, and that the address on the reverse coheres with the case the file describes.

  4. Run a forensic check on the file

    The check letter does the structural work, and the print does the rest. TamperCheck runs 200+ forensic checks including check-letter recomputation and patch detection, returning a risk score from 0 to 100 with findings tied to specific regions of the image.

Frequently asked questions

What do the letters in an NRIC number mean?

The first letter marks holder class and birth cohort, with S and T for citizens and F and G for permanent residents, while the final letter is a check character computed from the rest. The structure makes invented numbers fail their own checksum.

Can you tell citizenship from an NRIC?

The prefix is the tell: S and T belong to citizens and F and G to permanent residents. A card whose stated status contradicts its prefix is internally inconsistent, and that contradiction is checkable without any external database.

Why do older NRICs look different?

ICA has issued several editions as materials moved from PVC to polycarbonate, and all remain legitimate evidence of identity at issue. Analysis judges each edition against its own design rather than expecting one template.

How does TamperCheck verify an NRIC?

TamperCheck recomputes the check letter, weighs the prefix against the claimed status, and inspects the portrait and address regions for localised patching. It runs on a single REST endpoint, processes uploads ephemerally without storing them, and returns findings tied to specific regions.

TamperCheck analyses nric (singapore national id) uploads with a hybrid forensic and AI pipeline tuned for this document class. Upload endpoints accept PDF and common image formats; class is inferred automatically. See the API documentation for authentication, async jobs, and webhooks.

Related document types

All supported document types