activity
20182021
collaborators

6 papers

cs.LG2021

Unsupervised Information Obfuscation for Split Inference of Neural Networks

Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn +3

Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test quer…

stat.ML2020

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

Aleksei Triastcyn, Boi Faltings

This paper considers the problem of enhancing user privacy in common machine learning development tasks, such as data annotation and inspection, by substituting the real data with…

cs.LG2019

Federated Learning with Bayesian Differential Privacy

Aleksei Triastcyn, Boi Faltings

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy f…

stat.ML2019

Federated Generative Privacy

Aleksei Triastcyn, Boi Faltings

In this paper, we propose FedGP, a framework for privacy-preserving data release in the federated learning setting. We use generative adversarial networks, generator components of…

cs.LG2019

Bayesian Differential Privacy for Machine Learning

Aleksei Triastcyn, Boi Faltings

Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on sp…

cs.LG2018

Generating Artificial Data for Private Deep Learning

Aleksei Triastcyn, Boi Faltings

In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use…