Privacy-preserving machine learning aims to train models on private data...
The ability to generate privacy-preserving synthetic versions of sensiti...
Differential Privacy (DP) provides a formal privacy guarantee preventing...
We propose a novel method for training deep neural networks that are cap...
This is a short note on the performance of the ALI-G algorithm (Berrada ...
We propose a general framework for verifying input-output specifications...
The majority of modern deep learning models are able to interpolate the ...
Learning a deep neural network requires solving a challenging optimizati...
The top-k error is a common measure of performance in machine learning a...
We present a novel layerwise optimization algorithm for the learning
obj...