Dmitrii Usynin | DeepAI

AI Chat

Featured Co-authors

Daniel Rueckert
199 publications
Georgios Kaissis
52 publications
Kerstin Hammernik
21 publications
Johannes C. Paetzold
21 publications
Alexander Ziller
20 publications
Rickmer Braren
20 publications
Jonathan Passerat-Palmbach
16 publications
Andrew Trask
14 publications
Moritz Knolle
11 publications
Marcus R. Makowski
8 publications
Tamara T. Mueller
7 publications

∙ 05/04/2023

Leveraging gradient-derived metrics for data selection and valuation in differentially private training

Obtaining high-quality data for collaborative training of machine learni...

0 Dmitrii Usynin, et al. ∙

∙ 12/02/2022

Membership Inference Attacks Against Semantic Segmentation Models

Membership inference attacks aim to infer whether a data record has been...

0 Tomáš Chobola, et al. ∙

∙ 11/18/2022

How Do Input Attributes Impact the Privacy Loss in Differential Privacy?

Differential privacy (DP) is typically formulated as a worst-case privac...

0 Tamara T. Mueller, et al. ∙

∙ 05/05/2022

Can collaborative learning be private, robust and scalable?

We investigate the effectiveness of combining differential privacy, mode...

0 Dmitrii Usynin, et al. ∙

∙ 03/17/2022

SoK: Differential Privacy on Graph-Structured Data

In this work, we study the applications of differential privacy (DP) in ...

0 Tamara T. Mueller, et al. ∙

∙ 03/01/2022

Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks

Collaborative machine learning settings like federated learning can be s...

0 Dmitrii Usynin, et al. ∙

∙ 02/05/2022

Differentially Private Graph Classification with GNNs

Graph Neural Networks (GNNs) have established themselves as the state-of...

0 Tamara T. Mueller, et al. ∙

∙ 12/21/2021

Distributed Machine Learning and the Semblance of Trust

The utilisation of large and diverse datasets for machine learning (ML) ...

0 Dmitrii Usynin, et al. ∙

∙ 10/07/2021

Complex-valued deep learning with differential privacy

We present ζ-DP, an extension of differential privacy (DP) to complex-va...

0 Alexander Ziller, et al. ∙

∙ 09/22/2021

Partial sensitivity analysis in differential privacy

Differential privacy (DP) allows the quantification of privacy loss when...

0 Tamara T. Mueller, et al. ∙

∙ 09/22/2021

An automatic differentiation system for the age of differential privacy

We introduce Tritium, an automatic differentiation-based sensitivity ana...

0 Dmitrii Usynin, et al. ∙

∙ 09/22/2021

A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index

The Gaussian mechanism (GM) represents a universally employed tool for a...

0 Georgios Kaissis, et al. ∙

∙ 07/30/2021

NeuralDP Differentially private neural networks by design

The application of differential privacy to the training of deep neural n...

19 Moritz Knolle, et al. ∙

∙ 07/09/2021

Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty

We show that differentially private stochastic gradient descent (DP-SGD)...

0 Moritz Knolle, et al. ∙

∙ 07/09/2021

Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation

In recent years, formal methods of privacy protection such as differenti...

0 Alexander Ziller, et al. ∙

∙ 07/06/2021

Differentially private federated deep learning for multi-site medical image segmentation

Collaborative machine learning techniques such as federated learning (FL...

0 Alexander Ziller, et al. ∙

∙ 12/10/2020

Privacy-preserving medical image analysis

The utilisation of artificial intelligence in medicine and healthcare ha...

16 Alexander Ziller, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world