SOTAVerified

Image Classification with Differential Privacy

Image Classification with Differential Privacy is an improved version of the image classification task whereby the final classification output only describe the patterns of groups within the dataset while withholding information about individuals in the dataset.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–8 of 8 papers

TitleStatusHype
TAN Without a Burn: Scaling Laws of DP-SGDCode1
Toward Training at ImageNet Scale with Differential PrivacyCode1
Unlocking High-Accuracy Differentially Private Image Classification through ScaleCode1
Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imagingCode0
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser ModelsCode0
SmoothNets: Optimizing CNN architecture design for differentially private deep learningCode0
In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image ClassificationCode0
Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacyCode0
Show:102550

No leaderboard results yet.