Search Results for author:
Found 13 papers, 3 papers with code
Visual Privacy Auditing with Diffusion Models
We propose a reconstruction attack based on diffusion models (DMs) that assumes adversary access to real-world image priors and assess its implications on privacy leakage under DP-SGD.
SoK: Memorisation in machine learning
In this work we unify a broad range of previous definitions and perspectives on memorisation in ML, discuss their interplay with model generalisation and their implications of these phenomena on data privacy.
(Predictable) Performance Bias in Unsupervised Anomaly Detection
The empirical fairness laws discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition.
Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
Differentially private SGD (DP-SGD) holds the promise of enabling the safe and responsible application of machine learning to sensitive datasets.
How Do Input Attributes Impact the Privacy Loss in Differential Privacy?
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database.
Partial sensitivity analysis in differential privacy
However, while techniques such as individual R\'enyi DP (RDP) allow for granular, per-person privacy accounting, few works have investigated the impact of each input feature on the individual's privacy loss.
An automatic differentiation system for the age of differential privacy
We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML).
A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index
$\psi$ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation.
NeuralDP Differentially private neural networks by design
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 rigorous privacy guarantees to the individual.
Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models.
Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
Reconciling large-scale ML with the closed-form reasoning required for the principled analysis of individual privacy loss requires the introduction of new tools for automatic sensitivity analysis and for tracking an individual's data and their features through the flow of computation.
Differentially private federated deep learning for multi-site medical image segmentation
The application of PTs to FL in medical imaging and the trade-offs between privacy guarantees and model utility, the ramifications on training performance and the susceptibility of the final models to attacks have not yet been conclusively investigated.
Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial.
