Image Classification of Battle Tanks

September 20, 2011

An intriguing yet dubious anecdote about the development of an image classifier designed to distinguish between different types of battle tanks. Instead, the created model prioritized environmental attributes over tank characteristics, demonstrating the importance of responsible AI governance and trustworthy practices.

JOIN US at HISPI Project Cerebellum and help shape the Govern Map for preventing similar incidents through our Measure Manage framework.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MEASURE 2.12 — similarity 0.717, rank 1. TAIM detail and related incidents →
MEASURE 2.6 — similarity 0.716, rank 2. TAIM detail and related incidents →
MAP 1.1 — similarity 0.706, rank 3. TAIM detail and related incidents →

Alleged deployer: united-states-government
Alleged developer: united-states-government
Alleged harmed parties: united-states-government

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/29

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.