AI Harm Severity Scales by Category

Harm categories based on the CSET Harm Taxonomy: https://cset.georgetown.edu/wp-content/uploads/20230022-Adding-structure-to-AI-Harm-FINAL.pdf

Scores reflect impacts ranging from 0 (‘no harm’) to 10 ('worst-case catastrophe')

A review of the harm severity scale is planned follow-up work to ensure it supports specific user-requirements - feedback welcome.

Note: I have removed the 'Additional Definitions' and 'Other' categories from the CSET taxonomy and changed the 'Detrimental Content' category to 'Toxic or Malicious Content'.