A membership-inference-based scoring method, RecPS, quantifies privacy risk of individual interactions and users in recommender models, enabling fine-grained data removal.
California Consumer Privacy Act of 2018 (CCPA)
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.IR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RecPS: Privacy Risk Scoring for Recommender Systems
A membership-inference-based scoring method, RecPS, quantifies privacy risk of individual interactions and users in recommender models, enabling fine-grained data removal.