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 1–10 of 59 papers

TitleStatusHype
A Training Framework for Optimal and Stable Training of Polynomial Neural NetworksCode0
DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation—0
Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability—0
Just a Simple Transformation is Enough for Data Protection in Vertical Federated LearningCode0
Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation—0
DCT-CryptoNets: Scaling Private Inference in the Frequency DomainCode1
Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC—0
Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic DataCode2
Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task LearningCode0
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption—0
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.