RAND assesses eight of 38 weight-theft vectors as likely infeasible for OC1–OC3 but likely feasible for OC4 or OC5 under its defined capabilities

Name: RAND assesses eight of 38 weight-theft vectors as likely infeasible for OC1–OC3 but likely feasible for OC4 or OC5 under its defined capabilities
License: https://aidatacenterguide.com/terms#intellectual-property

8 of 38estimate

Value kind	estimate — Interpret this value according to its displayed kind, scope, source, and as-of date.
Scope	RAND 2024 expert assessment under its defined adversary capabilities, not a categorical impossibility statement. RAND's main text counts eight (printed p.18); its Table 5.2 scores nine vectors this way, and its summary says about a dozen are infeasible for non-state actors.
As of	2024-05-30
Source	RAND, Securing AI Model Weights, 30 May 2024, printed page 18 (PDF page 28).
Review	checking…review by 2027-04-16 · standard cadence
Recorded changes	last 2026-09-16 · 2 revisions tracked
Claim id	attack-vectors-infeasible-for-oc1-oc3-but

Where the guide uses it

11.1 Threat Model, Assets & Security Levels for AI Infrastructure

← Full numbers register — every date-stamped figure in the guide, with revision history.