AI-driven detection closes 1,250 counterfeit-label accounts at USPS

The USPS Office of Inspector General reports that 1,250 accounts generating counterfeit labels were closed from January 2026 as the result of AI-driven detection.

  • 2 for an organization

    The Postal Service closed 1,250 accounts that generated counterfeit labels in about seven months of 2026, a measured result that the Inspector General relays without re-performing the count.

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.

Size

No magnitude yet: distribution is not documented.

The system’s part
Not isolated. The white paper credits the closures to AI-driven detection using machine learning and computer vision. It gives no count of closures before the AI tools or without them, and it says that the image-based validation application was still being tested.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Risk
System
USPS AI-driven detection of counterfeit shipping labels (machine learning and computer vision, including image-based validation of labels and barcodes)
Made by
U.S. Postal Service (the paper names no vendor)
Used by
U.S. Postal Service
Where
United States (national)
Stage
Expanding
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Privacy protection (fraud detection)
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

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

    U.S. Postal Service Office of Inspector General, Research and Insights Solution Center. Postal Applications of Artificial Intelligence. RISC-WP-26-003, 3 August 2026.

    Since January 2026, 1,250 accounts generating counterfeit labels have been closed as the result of AI-driven detection.
    USPS uses multiple AI tools and platforms to identify counterfeit shipping labels and is continuing to expand AI use in this area.

Details

AI system

Workflow

USPS applied machine learning and computer vision to images of shipping labels and barcodes to confirm that postage was paid. USPS closed the accounts that generated counterfeit labels after the AI tools detected them.

Follow-up

Conditions for replication

Label and barcode images must be captured during processing so that the models can validate them. Staff must act on detections by closing the accounts.

Entry details

Sector

Postal services.

Purpose

The U.S. Postal Service built its AI-driven detection tools to identify counterfeit shipping labels and the accounts that generate them.

31 more questions 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 benefit

Peter H. Vartanian. (2026). AI-driven detection closes 1,250 counterfeit-label accounts at USPS (AIBD-1178). Artificial Intelligence Benefits Database, edition of 2 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1178.html (archived at https://doi.org/10.7910/DVN/AADSII, version 9.0)

BibTeX Data Field definitions