The paper claims that gradient ascent on forget samples makes them out-of-distribution for an unlearned image-to-image model, with formal guarantees and a data-poisoning audit.
In: 2021 IEEE Symposium on Security and Privacy (SP), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention
The paper claims that gradient ascent on forget samples makes them out-of-distribution for an unlearned image-to-image model, with formal guarantees and a data-poisoning audit.