← Search

Úlfar Erlingsson

2 accepted papers

2021

Tempered Sigmoid Activations for Deep Learning with Differential Privacy

AAAI 2021technical

Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer differential privacy for training data. In practice, this has been mostly an afterthought, with privacy-preserving models obtained by re-running training with a different optimizer, but using…

Cited by 203SourcePDFScholar
2017

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

ICLR 2017oral

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore reveal sensitive information. To address t…

Cited by 1306SourcecodeScholar