Dmitrii Usynin

Agustín Freitas Pasqualini

Isao Echizen

CoRR, 2024

Naturally Private Recommendations with Determinantal Point Processes.

[BibT_eX]

[DOI]

Jack K. Fitzsimons

Robert Pisarczyk

CoRR, 2024

Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training.

[BibT_eX]

[DOI]

Proceedings of the European Interdisciplinary Cybersecurity Conference, 2024

2023

Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks.

[BibT_eX]

[DOI]

ACM Trans. Priv. Secur., August, 2023

Differentially Private Graph Neural Networks for Whole-Graph Classification.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., June, 2023

SoK: Memorisation in machine learning.

[BibT_eX]

[DOI]

Moritz Knolle

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Membership Inference Attacks Against Semantic Segmentation Models.

[BibT_eX]

[DOI]

Tomás Chobola

Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2023

2022

Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning.

[BibT_eX]

[DOI]

Proc. Priv. Enhancing Technol., 2022

Unified Interpretation of the Gaussian Mechanism for Differential Privacy Through the Sensitivity Index.

[BibT_eX]

[DOI]

J. Priv. Confidentiality, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Can collaborative learning be private, robust and scalable?

[BibT_eX]

[DOI]

CoRR, 2022

SoK: Differential Privacy on Graph-Structured Data.

[BibT_eX]

[DOI]

CoRR, 2022

Differentially Private Graph Classification with GNNs.

[BibT_eX]

[DOI]

CoRR, 2022

Can Collaborative Learning Be Private, Robust and Scalable?

[BibT_eX]

[DOI]

Proceedings of the Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health, 2022

2021

Adversarial interference and its mitigations in privacy-preserving collaborative machine learning.

[BibT_eX]

[DOI]

Nat. Mach. Intell., 2021

End-to-end privacy preserving deep learning on multi-institutional medical imaging.

[BibT_eX]

[DOI]

Alexander Ziller

Marc-Matthias Steinborn

Nat. Mach. Intell., 2021

Distributed Machine Learning and the Semblance of Trust.

[BibT_eX]

[DOI]

Alexander Ziller

CoRR, 2021

Complex-valued deep learning with differential privacy.

[BibT_eX]

[DOI]

CoRR, 2021

Partial sensitivity analysis in differential privacy.

[BibT_eX]

[DOI]

CoRR, 2021

An automatic differentiation system for the age of differential privacy.

[BibT_eX]

[DOI]

CoRR, 2021

Differentially private training of neural networks with Langevin dynamics forcalibrated predictive uncertainty.

[BibT_eX]

[DOI]

CoRR, 2021

Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

2020

Privacy-preserving medical image analysis.

[BibT_eX]

[DOI]

Alexander Ziller

Théo Ryffel