Presents a systematic framework for evaluating MIAs across the full ML pipeline with standardized threat models and complementary metrics for different cost scenarios.
Unified gradient-based machine unlearning with remain geometry enhancement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
Presents a systematic framework for evaluating MIAs across the full ML pipeline with standardized threat models and complementary metrics for different cost scenarios.