.png){kind=icon}
Return
Privacy-preserving nearest prototype classifier
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.132673.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• lightweight NPC models are trainable in encrypted spaces using fully homomorphic encryption. • TFHE is not the best suited encryption scheme for LVQ due to large encryption matrices in the ciphertext-ciphertext multiplication. • learning distance based models on integer rings need to be handled with care due to wrap-arounds. • learning with integers on datasets rounded to small integer ranges achieve surprisingly high accuracies.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers
ShareSaveInterpretable machine learning: Fundamental principles and 10 grand challenges.png)
STATISTICS SURVEYS
OAAI
STATISTICS SURVEYSIF15.4
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveUnderstanding Data Breach from a Global Perspective: Incident Visualization and Data Protection Law ReviewDataOAAI
DataIF0
OAAIShareSaveShareSave
View more