SOTAVerified

Privacy Preserving Deep Learning

The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 31–40 of 59 papers

TitleStatusHype
The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning—0
A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component—0
Communication-Efficient Federated Distillation with Active Data Sampling—0
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption—0
DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation—0
Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning—0
Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning—0
DP-FP: Differentially Private Forward Propagation for Large Models—0
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning—0
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning—0
Show:102550
← PrevPage 4 of 6Next →

No leaderboard results yet.