Can I read Quantifying and Mitigating Privacy Risks of Contrastive Learning on EtoBox?

Quantifying and Mitigating Privacy Risks of Contrastive Learning by Xinlei He and Yang Zhang is a book available to read on EtoBox.

What is Quantifying and Mitigating Privacy Risks of Contrastive Learning about?

Abstracting tasks, self-supervised learning has been introduced [34].arXiv:2102.04140v2 [cs.LG] 21 Sep 2021Data is the key factor to drive the development of machinelearning (ML) during the past decade. However, high-qualitydata, in particular labeled data, is often hard and expensive to collect. To leverage large-scale unlabeled data, selfsupervised learning, represented by contrastive learning, isintroduced. The objective of contrastive learning is to mapdifferent views derived from a training sample (e.g., throughdata augmentation) closer in their representation space, whiledifferent views derived from different samples more distant. In this way, a contrastive model learns to generate informative representations for data samples, which are thenused to perform downstream ML tasks. Recent researchhas shown that machine learning models are vulnerable tovarious privacy attacks. However, most of the current efforts concentrate on models trained with supervised learning. Meanwhile, data samples’ informative representationslearned with contrastive learning may cause severe privacyrisks as well.In this paper, we perform the first privacy analysis of contrastive learning through t

Author

Xinlei He and Yang Zhang

Published

2025

Language

EN