KEA's facial recognition app exposes a forged CET admit card

AI system

System: Karnataka Examinations Authority QR code-based facial recognition app (CET-2025 candidate verification)
Model: Not assessed
Release: Not assessed
Application developer: Karnataka Examinations Authority (The Hindu and ETV Bharat: 'developed by KEA'; no vendor named)
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Admit cards printed with a QR code that resolves to the candidate's registered record and photograph. A photo pasted over the card therefore does not change what the app compares against. A live photograph taken at the hall door and matched by the app against the registered photo before entry. This ran at every center rather than the earlier pilot subset. Center staff instructed to act on a mismatch and escalate to the principal and KEA. Video coverage of the entrance that KEA could call for afterwards.
Human oversight: Examination staff scanned the admit card, captured the photograph, and acted on the mismatch.
Relation to AI: The app did the detecting. Staff scanned the admit card's QR code and captured the woman's photo. It flagged a mismatch with the photo on record (New Indian Express). It “revealed that she was not the genuine candidate” (The Hindu). The Hindu and the Times of India both report the forged card's contents. It carried her own photograph with the genuine candidate's hall ticket number and QR code. Comparing the card with her face would therefore not have exposed her. The flag depended on the app's match against the registered photograph. Staff then acted, but she fled before the principal was told. No arrest or sanction is attributable to the system. KEA's probe and the promised legal action were still pending in every report.
AI contribution: The examination app compared a captured photograph with the registered candidate’s photograph and flagged a mismatch. Comparing the person only with the forged admit card would not have exposed the substitution.

Benefits

Outcome identifiers: Not assessed
Benefit: KEA's facial recognition app flagged a woman with a forged CET admit card in Bengaluru on 17 April 2025; she fled before writing the paper.
Category: Reduced Risk
Status: Not assessed
Beneficiary groups: Organizations. Society.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Measurement

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: Not assessed
Comparison: Not assessed
Results: Not assessed
Additional value from AI: Not assessed
Limitations: The person left before the principal was informed. The reports describe a pending investigation and do not establish an arrest or sanction.
Denominators: Not assessed
Materials for replication: Not assessed

Money

Kind of value: Not assessed
Amount: Not assessed
Currency and prices: Not assessed
Period and unit: Not assessed
Realization: Not assessed
Recipients and payers: Not assessed
Gross or net: Not assessed
Included costs: Not assessed
Comparison: Not assessed
Method: Not assessed
Return and payback: Not assessed

People and places

Participants: Developer: Karnataka Examinations Authority (The Hindu and ETV Bharat: 'developed by KEA'; no vendor named). Operator: Karnataka Examinations Authority.
Jurisdictions: Benefit: Bengaluru, India.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Follow-up

Conditions for replication: The registered photograph must be of the genuine candidate. The control fails if the fraud is committed at registration rather than at the door. Verification must be completed before the candidate is admitted. This depends on staffing and app reliability at scale. KEA reported no glitches this time. A flagged person must be detained or identified on the spot. Here she fled, so the deterrent rests on the probe and the video footage rather than on an arrest.
Replication attempts: Not assessed
Later findings: 22 April 2026. A year later KEA announced that facial recognition and QR-code verification would again be done for every candidate at K-CET 2026 on 23-24 April 2026.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Evidence

Source numbers: AIBD-0128-source-0001–0007
Citations: Numbered references below.
Language: Not assessed
Source relationships: Independent
Original evidence: Not assessed
Access and versions: Not assessed
Supported findings: Not assessed
Evidence links: Not assessed
Evidence strength: Not assessed
Missing evidence: Not assessed

Grades

Assessed benefits: Organizations. Society.
Depth: Organizations: 2. Society: 1.
Reasons: Organizations: KEA stopped a forged-entry attempt in the app's first state-wide run. The Hindu reports that all verifications ran without technical glitches on the second day. The benefit to the authority is a working integrity control across 3,30,808 registrants, demonstrated on one case. Society: Genuine CET-2025 candidates: one person who was not the candidate on record was kept out of a competition for seats among 3.3 lakh registrants. It is a small benefit spread across the cohort. The sources do not say what she meant to gain.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Entry details

Kind: Not assessed
Related entries: Not assessed
Field: Education (state entrance examinations). Public sector examination administration.
Purpose: KEA built the app to verify candidates at the hall entrance and prevent impersonation. It scans the admit card's QR code and matches a live photograph against the photo submitted at registration. Exposing this impersonator was exactly that purpose.
Dates: Date basis unassessed: 2025 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 130ac3437aa9…

References

Other identifiers: oecd_aim: 2025-04-14-e47b.
Category mappings: Not assessed
Brief: Not assessed
Revisions: 5 revisions. Latest: 21 October 2026.

Sources

News report Independent author

The Hindu Bureau (2025). CET: Impersonator caught using facial recognition app, probe ordered. The Hindu, Bengaluru, 17 April 2025.
News report Independent author

The Times of India (2025). Facial recognition app foils impersonation attempt at Bengaluru CET centre. The Times of India, Bengaluru, 17 April 2025.
News report Independent author

Express News Service (2025). QR code facial recognition app exposes impersonator in Bengaluru. The New Indian Express, 18 April 2025.
News report Independent author

ETV Bharat (2025). Proxy CET Examinee Caught Red-Handed In Karnataka, Investigation On. ETV Bharat, 18 April 2025.
News report Independent author

The Times of India (2025). Karnataka Common Entrance Test set to begin with new security norms for candidates. The Times of India, Bengaluru, 14 April 2025.
News report Independent author

ETV Bharat (2026). Karnataka Examination Authority All Set To Conduct K-CET On April 23, 24. ETV Bharat, 22 April 2026.
Registry label Independent author

OECD AI Incidents Monitor, incident 2025-04-14-e47b