42 citations · 80 across the 28 of their papers we have counts for
11 papers · 1 filter
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…
On Arbitrary Predictions from Equally Valid Models
Sarah Lockfisch, Kristian Schwethelm, Martin Menten +4
Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In m…
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…
From Mean to Extreme: Formal Differential Privacy Bounds on the Success of Real-World Data Reconstruction Attacks
Anneliese Riess, Kristian Schwethelm, Johannes Kaiser +4
The gold standard for privacy in machine learning, Differential Privacy (DP), is often interpreted through its guarantees against membership inference. However, translating DP budg…
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…
Differentially private training of residual networks with scale normalisation
Helena Klause, Alexander Ziller, Daniel Rueckert +2
The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs. In this wo…
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…
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…