dp-sgd
Country:
- South America > Chile > Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- Europe > Switzerland > Vaud > Lausanne (0.04)
- Europe > Germany > Bavaria > Upper Bavaria > Munich (0.04)
Technology:
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
This paper presents an auditing procedure for the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm in the black-box threat model that is substantially tighter than prior work.
Country:
- North America > United States > California > Riverside County > Riverside (0.04)
- Asia > Singapore (0.04)
Industry:
- Information Technology > Security & Privacy (0.93)
- Transportation > Air (0.63)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.87)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.68)
Technology:
Amplified Banded Matrix Factorization A unified approach to private training
MF mechanism consistently performs at least as well as the best prior methods.
Country:
- North America > United States (0.14)
- Europe > Switzerland > Zürich > Zürich (0.14)
- Europe > United Kingdom > England > Greater London > London (0.04)
Genre:
- Workflow (0.46)
- Research Report > New Finding (0.45)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Security & Privacy (0.92)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
A common approach for private training of differentiable models, such as neural networks, is to apply first-order methods with noisy gradients.
Genre:
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (1.00)
Technology:
Country:
- North America > United States > New York > New York County > New York City (0.04)
- Europe > Russia > Northwestern Federal District > Leningrad Oblast > Saint Petersburg (0.04)
- Asia > Russia (0.04)
- (3 more...)
Technology:
- Information Technology > Security & Privacy (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.67)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.46)
Country:
- North America > United States (0.04)
- Europe > Italy > Sicily (0.04)
- Asia > Middle East > Jordan (0.04)
Technology:
Technology:
Country:
- North America > United States > Michigan > Washtenaw County > Ann Arbor (0.04)
- North America > Dominican Republic (0.04)
- Europe > Spain > Catalonia > Barcelona Province > Barcelona (0.04)
- (3 more...)
Technology: