KNT applies key-conditioned nonlinear obfuscation to split-inference features, cutting re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and under 1 pp accuracy loss.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
GPT-4o achieves macro F1 scores of 0.89 for politician face recognition and 0.86 for person counting in election Instagram stories, outperforming FaceNet512, RetinaFace, and Google Cloud Vision.
Stacking seven black-box estimators into a meta-classifier reveals persistent membership leakage in differentially private federated learning models at epsilon=200 on NIST genomics data, outperforming single-signal baselines.
Proposes bearing-wise data partitioning to remove leakage in ML bearing fault diagnosis, reformulates as multi-label classification, and shows training bearing count drives generalization on four public datasets.
FedReLa applies feature-dependent re-labeling to correct biased global decision boundaries in imbalanced federated learning without requiring knowledge of the global class distribution.
citing papers explorer
-
Towards a more realistic evaluation of machine learning models for bearing fault diagnosis
Proposes bearing-wise data partitioning to remove leakage in ML bearing fault diagnosis, reformulates as multi-label classification, and shows training bearing count drives generalization on four public datasets.