2 papers
cs.LG2026
A Sharp Transition in Data Reconstruction under Differential Privacy
Max Cairney-Leeming, Simone Bombari, Marco Mondelli
Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivating defenses with guarantees th…
cs.LG2026
Adaptive Sampling and Clipping for Private Worst-Case Group Optimization
Max Cairney-Leeming, Amartya Sanyal, Christoph H. Lampert
A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they should work comparably well for ind…