39 citations · 61 across the 19 of their papers we have counts for
19 papers
Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models
Asia Belfiore, Jonathan Passerat-Palmbach, Dmitrii Usynin
The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explore…
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
Olivia Ma, Jonathan Passerat-Palmbach, Dmitrii Usynin
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Priv…
SoK: Memorisation in machine learning
Dmitrii Usynin, Moritz Knolle, Georgios Kaissis
Quantifying the impact of individual data samples on machine learning models is an open research problem. This is particularly relevant when complex and high-dimensional relationsh…
Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) regulatory concerns and B) a lack of data owner incentives to…
Membership Inference Attacks Against Semantic Segmentation Models
Tomas Chobola, Dmitrii Usynin, Georgios Kaissis
Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this ca…
How Do Input Attributes Impact the Privacy Loss in Differential Privacy?
Tamara T. Mueller, Stefan Kolek, Friederike Jungmann +5
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database. More recently, extensions to individual subjects or their at…
Can collaborative learning be private, robust and scalable?
Dmitrii Usynin, Helena Klause, Johannes C. Paetzold +2
In federated learning for medical image analysis, the safety of the learning protocol is paramount. Such settings can often be compromised by adversaries that target either the pri…
SoK: Differential Privacy on Graph-Structured Data
Tamara T. Mueller, Dmitrii Usynin, Johannes C. Paetzold +2
In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of gra…
Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion atta…
Differentially Private Graph Classification with GNNs
Tamara T. Mueller, Johannes C. Paetzold, Chinmay Prabhakar +3
Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein inte…
Distributed Machine Learning and the Semblance of Trust
Dmitrii Usynin, Alexander Ziller, Daniel Rueckert +2
The utilisation of large and diverse datasets for machine learning (ML) at scale is required to promote scientific insight into many meaningful problems. However, due to data gover…
A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index
Georgios Kaissis, Moritz Knolle, Friederike Jungmann +3
The Gaussian mechanism (GM) represents a universally employed tool for achieving differential privacy (DP), and a large body of work has been devoted to its analysis. We argue that…
Partial sensitivity analysis in differential privacy
Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin +4
Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the pro…
An automatic differentiation system for the age of differential privacy
Dmitrii Usynin, Alexander Ziller, Moritz Knolle +4
We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML). Optimal noise calibration in this set…
Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
Alexander Ziller, Dmitrii Usynin, Moritz Knolle +6
In recent years, formal methods of privacy protection such as differential privacy (DP), capable of deployment to data-driven tasks such as machine learning (ML), have emerged. Rec…
NeuralDP Differentially private neural networks by design
Moritz Knolle, Dmitrii Usynin, Alexander Ziller +3
The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigo…
Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
Moritz Knolle, Alexander Ziller, Dmitrii Usynin +4
We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety…
Differentially private federated deep learning for multi-site medical image segmentation
Alexander Ziller, Dmitrii Usynin, Nicolas Remerscheid +5
Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer. Recent initiatives hav…
Privacy-preserving medical image analysis
Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel +8
The utilisation of artificial intelligence in medicine and healthcare has led to successful clinical applications in several domains. The conflict between data usage and privacy pr…