Skip to the card

Card 598 of 9932026-09-20 issue

Observed arrival · 2026-09-20

OSAFIS Maps the Security Boundaries of Intelligent Systems

osafis.org Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

An open research framework for assessing AI security across nine domains, 23 security properties, and 12 attack mechanisms.

Landing page captured for the 2026-09-20 issue.
For
AI security researchers and assessment engineers
Worth noticing
Its nine domains are stable identifiers, not a severity ranking or execution sequence.

Field notes

OSAFIS organizes its proposal around typed relationships such as delegated authority, actions, feedback, and state synchronization. The site distinguishes security properties from intervention mechanisms, test outcomes, evidence facets, and registry decisions, while warning that its architectural examples have not been executed or validated. A 13-document research library includes threat modeling, assessment methods, version identifiers, related frameworks, and worked examples. The current release is labeled 2.0.0-draft.1.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

Mahjongg With Footnotes

304,744 arrived 1,000 judged 993 catalogued Enter the complete issue
osafis.org

Landing page observed 2026-09-20. The live site may have changed.