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

Showing 2650 of 59 papers

TitleStatusHype
Backpropagation Clipping for Deep Learning with Differential PrivacyCode0
DP-FP: Differentially Private Forward Propagation for Large Models0
SoK: Privacy-preserving Deep Learning with Homomorphic Encryption0
Homogeneous Learning: Self-Attention Decentralized Deep LearningCode0
Towards Secure and Practical Machine Learning via Secret Sharing and Random PermutationCode0
Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep LearningCode0
Towards a Privacy-preserving Deep Learning-based Network Intrusion Detection in Data Distribution Services0
Antipodes of Label Differential Privacy: PATE and ALIBICode1
Variational Leakage: The Role of Information Complexity in Privacy LeakageCode0
CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUCode1
Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep LearningCode0
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models0
Can we Generalize and Distribute Private Representation Learning?Code0
Secure Data Sharing With Flow ModelCode0
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning0
Tempered Sigmoid Activations for Deep Learning with Differential PrivacyCode1
How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning0
MPC Protocol for G-module and its Application in Secure Compare and ReLU0
Security and Privacy Preserving Deep Learning0
Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks0
Locally Private Graph Neural NetworksCode1
ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret SharingCode1
Locally Differentially Private (Contextual) Bandits LearningCode0
Fawkes: Protecting Privacy against Unauthorized Deep Learning ModelsCode3
Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.