all AI news
Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning. (arXiv:2205.12430v1 [cs.LG])
May 26, 2022, 1:11 a.m. | Yunhao Yang, Parham Gohari, Ufuk Topcu
stat.ML updates on arXiv.org arxiv.org
We study the privacy risks that are associated with training a neural
network's weights with self-supervised learning algorithms. Through empirical
evidence, we show that the fine-tuning stage, in which the network weights are
updated with an informative and often private dataset, is vulnerable to privacy
attacks. To address the vulnerabilities, we design a post-training
privacy-protection algorithm that adds noise to the fine-tuned weights and
propose a novel differential privacy mechanism that samples noise from the
logistic distribution. Compared to the …
arxiv learning privacy self-supervised learning supervised learning
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineer, Machine Learning, Payments
@ Google | Bengaluru, Karnataka, India
Business Intelligence Analyst, Analytics and Data Science, YouTube
@ Google | Bengaluru, Karnataka, India