research
∙
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...
share
research
∙
12/02/2022
Membership Inference Attacks Against Semantic Segmentation Models
Membership inference attacks aim to infer whether a data record has been...
research
∙
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...
research
∙
05/05/2022
Can collaborative learning be private, robust and scalable?
We investigate the effectiveness of combining differential privacy, mode...
research
∙
03/17/2022
SoK: Differential Privacy on Graph-Structured Data
In this work, we study the applications of differential privacy (DP) in ...
research
∙
03/01/2022
Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks
Collaborative machine learning settings like federated learning can be s...
research
∙
02/05/2022
Differentially Private Graph Classification with GNNs
Graph Neural Networks (GNNs) have established themselves as the state-of...
research
∙
12/21/2021
Distributed Machine Learning and the Semblance of Trust
The utilisation of large and diverse datasets for machine learning (ML) ...
research
∙
10/07/2021
Complex-valued deep learning with differential privacy
We present ζ-DP, an extension of differential privacy (DP) to complex-va...
research
∙
09/22/2021
Partial sensitivity analysis in differential privacy
Differential privacy (DP) allows the quantification of privacy loss when...
research
∙
09/22/2021
An automatic differentiation system for the age of differential privacy
We introduce Tritium, an automatic differentiation-based sensitivity ana...
research
∙
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...
research
∙
07/30/2021
NeuralDP Differentially private neural networks by design
The application of differential privacy to the training of deep neural n...
research
∙
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)...
research
∙
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...
research
∙
07/06/2021
Differentially private federated deep learning for multi-site medical image segmentation
Collaborative machine learning techniques such as federated learning (FL...
research
∙
12/10/2020
