Passport photo FR matching exposes otherwise hidden identity fraud

The ANAO found that facial recognition matching of passport applications detected many identity frauds that would not otherwise have been found, about 22 recorded a year.

  • 2 an organization

    Matching detected identity frauds that the Passport Office would not otherwise have found, about 22 recorded a year, which the ANAO considers an undercount.

  • Not rated society

    Fraudulently obtained passports can support other crimes, but the audit does not measure harm prevented beyond the detected cases.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent audit report supports the benefit.

The system’s part
Not isolated. The ANAO relied on interviews, file reviews and the APO's own records of how each fraud was detected. It made no comparison with and without matching. It describes a commercially supplied biometric algorithm, the third new version since 2005, and does not say whether the algorithm learned from data.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Risk
System
Australian Passport Office facial recognition (FR) matching of applicants' photos against its image database (one-to-many)
Made by
A commercial supplier of the biometric algorithm (not named in the report)
Used by
Australian Passport Office, Department of Foreign Affairs and Trade
Where
Australia (national)
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Audit report, by authors with no tie to the system.

    Australian National Audit Office. Management of ePassports, Department of Foreign Affairs and Trade. Audit Report No.33 2011–12, 22 May 2012, paragraphs 4.16 to 4.20.

    In addition, while FR matching has detected many cases of identity fraud that would not otherwise have been detected, the incorrect recording of the detection method for some FR matches impairs the APO’s ability to accurately quantify the success of the FR system in detecting fraud.

Details

AI system

Workflow

A commercial algorithm converted each applicant's photo into a template and searched all other templates in the database. Eligibility officers reviewed the candidate matches and referred suspected frauds to the Passport Fraud Section.

Follow-up

Conditions for replication

The database must already hold a photo of the fraudster under another identity. Officers need training and tools to compare faces in candidate matches.

Entry details

Sector

Identity documents (passport issuing).

Purpose

A commercial supplier built the biometric algorithm to turn passport photos into templates that the Passport Office compares with every other template in its database.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Passport photo FR matching exposes otherwise hidden identity fraud (AIBD-0679). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0679.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions