Dmitrii Usynin

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 29

Top Topics

Machine Learning

Sensitivity Analysis

Differential Privacy

Differentially Private

Top Venues

Nat. Mach. Intell.

J. Priv. Confidentiality

Publications

Jack K. Fitzsimons, Agustín Freitas Pasqualini, Robert Pisarczyk, Dmitrii Usynin
Naturally Private Recommendations with Determinantal Point Processes. CoRR (2024)
Felix Hsieh, Huy H. Nguyen, AprilPyone MaungMaung, Dmitrii Usynin, Isao Echizen
Mitigating Backdoor Attacks using Activation-Guided Model Editing. CoRR (2024)
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training. EICC (2024)
Dmitrii Usynin, Moritz Knolle, Georgios Kaissis
SoK: Memorisation in machine learning. CoRR (2023)
Tamara T. Mueller, Johannes C. Paetzold, Chinmay Prabhakar, Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Differentially Private Graph Neural Networks for Whole-Graph Classification. IEEE Trans. Pattern Anal. Mach. Intell. 45 (6) (2023)
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Leveraging gradient-derived metrics for data selection and valuation in differentially private training. CoRR (2023)
Tomás Chobola, Dmitrii Usynin, Georgios Kaissis
Membership Inference Attacks Against Semantic Segmentation Models. AISec@CCS (2023)
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks. ACM Trans. Priv. Secur. 26 (3) (2023)
Dmitrii Usynin, Daniel Rueckert, Jonathan Passerat-Palmbach, Georgios Kaissis
Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning. Proc. Priv. Enhancing Technol. 2022 (1) (2022)
Tamara T. Mueller, Johannes C. Paetzold, Chinmay Prabhakar, Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Differentially Private Graph Classification with GNNs. CoRR (2022)
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks. CoRR (2022)
Tomás Chobola, Dmitrii Usynin, Georgios Kaissis
Membership Inference Attacks Against Semantic Segmentation Models. CoRR (2022)
Georgios Kaissis, Moritz Knolle, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Daniel Rueckert
Unified Interpretation of the Gaussian Mechanism for Differential Privacy Through the Sensitivity Index. J. Priv. Confidentiality 12 (1) (2022)
Dmitrii Usynin, Helena Klause, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis
Can Collaborative Learning Be Private, Robust and Scalable? DeCaF/FAIR@MICCAI (2022)
Dmitrii Usynin, Helena Klause, Daniel Rueckert, Georgios Kaissis
Can collaborative learning be private, robust and scalable? CoRR (2022)
Tamara T. Mueller, Dmitrii Usynin, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis
SoK: Differential Privacy on Graph-Structured Data. CoRR (2022)
Tamara T. Mueller, Stefan Kolek, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Daniel Rueckert, Georgios Kaissis
How Do Input Attributes Impact the Privacy Loss in Differential Privacy? CoRR (2022)
Dmitrii Usynin, Alexander Ziller, Marcus R. Makowski, Rickmer Braren, Daniel Rueckert, Ben Glocker, Georgios Kaissis, Jonathan Passerat-Palmbach
Adversarial interference and its mitigations in privacy-preserving collaborative machine learning. Nat. Mach. Intell. 3 (9) (2021)
Moritz Knolle, Dmitrii Usynin, Alexander Ziller, Marcus R. Makowski, Daniel Rueckert, Georgios Kaissis
NeuralDP Differentially private neural networks by design. CoRR (2021)
Georgios Kaissis, Moritz Knolle, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Daniel Rueckert
A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index. CoRR (2021)
Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Kritika Prakash, Andrew Trask, Rickmer Braren, Marcus R. Makowski, Daniel Rueckert, Georgios Kaissis
Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation. CoRR (2021)
Alexander Ziller, Dmitrii Usynin, Nicolas Remerscheid, Moritz Knolle, Marcus R. Makowski, Rickmer Braren, Daniel Rueckert, Georgios Kaissis
Differentially private federated deep learning for multi-site medical image segmentation. CoRR (2021)
Dmitrii Usynin, Alexander Ziller, Daniel Rueckert, Jonathan Passerat-Palmbach, Georgios Kaissis
Distributed Machine Learning and the Semblance of Trust. CoRR (2021)
Dmitrii Usynin, Alexander Ziller, Moritz Knolle, Daniel Rueckert, Georgios Kaissis
An automatic differentiation system for the age of differential privacy. CoRR (2021)
Moritz Knolle, Alexander Ziller, Dmitrii Usynin, Rickmer Braren, Marcus R. Makowski, Daniel Rueckert, Georgios Kaissis
Differentially private training of neural networks with Langevin dynamics forcalibrated predictive uncertainty. CoRR (2021)
Georgios Kaissis, Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel, Dmitrii Usynin, Andrew Trask, Ionésio Lima, Jason Mancuso, Friederike Jungmann, Marc-Matthias Steinborn, Andreas Saleh, Marcus R. Makowski, Daniel Rueckert, Rickmer Braren
End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nat. Mach. Intell. 3 (6) (2021)
Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Kerstin Hammernik, Daniel Rueckert, Georgios Kaissis
Complex-valued deep learning with differential privacy. CoRR (2021)
Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Friederike Jungmann, Daniel Rueckert, Georgios Kaissis
Partial sensitivity analysis in differential privacy. CoRR (2021)
Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel, Dmitrii Usynin, Andrew Trask, Ionésio Da Lima Costa Junior, Jason Mancuso, Marcus R. Makowski, Daniel Rueckert, Rickmer Braren, Georgios Kaissis
Privacy-preserving medical image analysis. CoRR (2020)