SAC-JC fingerprints deep models by comparing correlation matrices of model outputs on JPEG-compressed images, and extends this to face verification via binary reference-image features.
Sensitive-sample fingerprinting of deep neural net- works
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sample Correlation for Fingerprinting Deep Face Recognition
SAC-JC fingerprints deep models by comparing correlation matrices of model outputs on JPEG-compressed images, and extends this to face verification via binary reference-image features.