The authors define a contrastive relationship gap and use a one-tailed T-test to detect whether a suspect encoder was pre-trained on a target dataset.
Deep learning with differential privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dataset Ownership Verification in Contrastive Pre-trained Models
The authors define a contrastive relationship gap and use a one-tailed T-test to detect whether a suspect encoder was pre-trained on a target dataset.