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 1–25 of 59 papers

TitleStatusHype
Fawkes: Protecting Privacy against Unauthorized Deep Learning ModelsCode3
Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic DataCode2
ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret SharingCode1
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New DatasetCode1
DCT-CryptoNets: Scaling Private Inference in the Frequency DomainCode1
Antipodes of Label Differential Privacy: PATE and ALIBICode1
Split Without a Leak: Reducing Privacy Leakage in Split LearningCode1
Locally Private Graph Neural NetworksCode1
CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUCode1
Tempered Sigmoid Activations for Deep Learning with Differential PrivacyCode1
Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep LearningCode0
Locally Differentially Private (Contextual) Bandits LearningCode0
Just a Simple Transformation is Enough for Data Protection in Vertical Federated LearningCode0
Backpropagation Clipping for Deep Learning with Differential PrivacyCode0
A Training Framework for Optimal and Stable Training of Polynomial Neural NetworksCode0
Homogeneous Learning: Self-Attention Decentralized Deep LearningCode0
Memorization of Named Entities in Fine-tuned BERT ModelsCode0
Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task LearningCode0
Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imagingCode0
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)Code0
Collaborative Training of Medical Artificial Intelligence Models with non-uniform LabelsCode0
A generic framework for privacy preserving deep learningCode0
Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and UtilityCode0
Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI ModelsCode0
Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep LearningCode0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.