6 papers
Empirical Auditing of Edge-Private Graph Generators
Anum Fatima, Stratis Limnios, James Adams +4
We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower bounds on the privacy loss wit…
TASER: Task-Aware Stein Regularisation for Geometry-Driven Smoothness
Michał Kozyra, Gesine Reinert
Deep neural networks remain sensitive to distribution shifts, motivating regularisation informed by data geometry. We introduce TASER (Task-Aware Stein Regularisation), a compact t…
A Universal Nearest-Neighbor Estimator for Intrinsic Dimensionality
Eng-Jon Ong, Omer Bobrowski, Gesine Reinert +1
Estimating the intrinsic dimensionality (ID) of data is a fundamental problem in machine learning and computer vision, providing insight into the true degrees of freedom underlying…
FraudTransformer: Time-Aware GPT for Transaction Fraud Detection
Gholamali Aminian, Andrew Elliott, Tiger Li +8
Detecting payment fraud in real-world banking streams requires models that can exploit both the order of events and the irregular time gaps between them. We introduce FraudTransfor…
Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance
Leoni Carla Wirth, Gholamali Aminian, Gesine Reinert
Networks are popular for representing complex data. In particular, differentially private synthetic networks are much in demand for method and algorithm development. The network ge…
Generalization and Robustness of the Tilted Empirical Risk
Gholamali Aminian, Amir R. Asadi, Tian Li +3
The generalization error (risk) of a supervised statistical learning algorithm quantifies its prediction ability on previously unseen data. Inspired by exponential tilting, \citet{…