.png){kind=icon}
返回
Supervised Machine Learning with Plausible Deniability
.png){kind=icon}
OA
AI
DOI：10.1016/j.cose.2021.102506.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data or, equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends beyond non-recoverability towards plausible deniability: Given a ML model f, we show that one can take a set of purely random training data, and from this define a suitable learning rule that will produce a ML model that is exactly f. Thus, any speculation about which data has been used to train f is deniable upon the claim that any other data could have led to the same results. We corroborate our theoretical finding with practical examples and open source implementations of how to find the learning rules for a chosen set of training data. (c) 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
Keyword:
Machine Learning
Plausible Deniability
Privacy
Data Protection
Artificial Intelligence
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
5.4
论文数:
4.6K
被引数:
1.4W
机构
引用论文
A machine-learning based approach to privacy-aware information-sharing in mobile social networksOAAI
OAAI分享收藏Machine learning and genomics: precision medicine versus patient privacy.png)
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCESOAAI
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCESIF3.7
OAAI分享收藏“I put it in my head that the supplement would help me”: Open-placebo improves exercise performance in female cyclistsPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
没有更多内容
没有更多内容