Case Study — Community College

1 in 3 applications
were not real.

$13M gone to students who never existed. AI-generated ghost students enrolled, submitted AI-written coursework, collected Pell Grants, and disappeared. 116 campuses. 2.1 million real students competing for slots and aid against an army of synthetic identities.

This is the fraud you cannot spot with a human in the loop. Forty-eight applications from the same IP in two minutes. The suss. API catches it at submission.

All case studies
What happened
  1. 01
    Fake applications at scale
    Fraudsters used stolen and synthetic identities to submit hundreds of applications programmatically. At some colleges, 50 applications arrived within two seconds.
  2. 02
    AI-generated coursework
    Ghost students attended class by submitting AI-written assignments. They looked active enough to maintain enrollment and avoid triggering academic flags.
  3. 03
    Financial aid disbursement
    Pell Grants and state aid were disbursed to newly opened accounts. Maximum aid of $7,395 per semester per ghost student, multiplied across thousands of fake enrollees.
SourceU.S. Department of Education OIG ↗
What it cost
$13M
Lost in state and federal funds
116
Campuses affected statewide
223K+
Fraudulent enrollments flagged
What suss. would have surfaced

A signed record, before the wire.

suss. interaction recordFlagged
Ghost Student Enrollment Fraud Detected

This is the kind of message your people see, before they act on it. Plain guidance, not a number.

  • Hold all financial aid disbursement for this application.
  • Flag the IP block for velocity analysis. 48 applications in 120 seconds is not human behavior.
  • Verify SSN through the Social Security Administration before processing enrollment.
  • Cross-reference mailing address against known commercial mail drops.
  • Run AI detection on the personal statement and submitted coursework.
  • Report to the U.S. Department of Education Office of Inspector General.
signed9c2f…e7a1· queryable record
Why this keeps happening

Why ghost students are invisible to humans.

Ghost students look real
They enroll in classes, submit assignments, and maintain activity. From the registrar's perspective, they are indistinguishable from real students.
AI-generated work passes human review
Coursework is generated by large language models and submitted on schedule. Individual professors cannot detect synthetic work across hundreds of students.
Synthetic identities have no prior record
These are not stolen identities with fraud alerts. They are fabricated from scratch, with SSNs that pass basic validation but have no credit history.
Volume overwhelms manual verification
Community colleges process hundreds of thousands of applications. Manual identity verification at this scale is not feasible.
The divergence
Without suss.
  1. Application arrives. Passes basic validation.
  2. Synthetic SSN has no fraud alert on file.
  3. Student enrolls and submits AI-written work.
  4. Pell Grant disbursed to a newly opened account.
  5. Ghost student cashes out and disappears.
  6. $13M drained across the system before anyone notices.
With suss.
  1. Application flagged on submission.
  2. Synthetic SSN and missing digital footprint detected.
  3. Velocity anomaly: 48 apps from same IP in 2 minutes.
  4. AI-generated personal statement flagged before enrollment.
  5. Financial aid hold triggered before disbursement.
  6. $13M protected. Real students get their slots and aid.

Want this catching the next one before it ships?

This is a documented incident with a public source. The next one is in someone's inbox right now. suss. is what catches it.

Read more case studies