Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.
Forgetting outside the box: Scrubbing deep networks of informa- tion accessible from input-output observations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.