Skip to content
BLOKZ.dev

The Unlearning Gap

What unlearning verification reports as 'forgotten' versus what a recovery attack gets back. Each method's dumbbell runs from its verdict (MIA ≈ random) to what an attack recovers — 0.97–0.99 for cheap methods. Toggle to % recoverable; tap a method. The ZK proof's scope ends at the verdict.

chart SVG Machine LearningSecurity Jun 19, 2026
⬢ loading artifact…
The Unlearning Gap — tap a method (or ← →) to read its detail · toggle metric: MIA AUC ↔ % knowledge recoverable · data as of · UMA (Xuan & Li 2025), ZK-APEX (Maheri et al. 2025), SISA (Bourtoule et al. 2021) ↗ open artifact ↗

View artifact source on GitHub ↗

Appears in

Type to search the archive.