20 citations · 26 across the 15 of their papers we have counts for
16 papers
Memorisation bias in medical AI
Moritz A. Knolle, Martin J. Menten, Laurin Lux +5
Medical AI models hold immense potential to improve patient outcomes, but they are also known to unintentionally memorise individual records from their training datasets. While suc…
Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
Laurin Lux, Alexander H. Berger, Moritz Knolle +2
Region-based loss functions, such as the Dice loss, have established themselves as the de facto standard for highly class- and region-imbalanced segmentation tasks. However, models…
Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation
Adil Koeken, Alexander Ziller, Moritz Knolle +1
The generation of privacy-preserving synthetic datasets is a promising avenue for overcoming data scarcity in medical AI research. Post-hoc privacy filtering techniques, designed t…
Visual Privacy Auditing with Diffusion Models
Kristian Schwethelm, Johannes Kaiser, Moritz Knolle +3
Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks usin…
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…
(Predictable) Performance Bias in Unsupervised Anomaly Detection
Felix Meissen, Svenja Breuer, Moritz Knolle +5
Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promi…
Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
Moritz Knolle, Robert Dorfman, Alexander Ziller +2
Differentially private SGD (DP-SGD) holds the promise of enabling the safe and responsible application of machine learning to sensitive datasets. However, DP-SGD only provides a bi…
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…
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…
Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
Moritz Knolle, Georgios Kaissis, Friederike Jungmann +5
For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial. For example, existent segmentat…