按年被提到
20142015 · 2 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1412.6181 · cs.LG

Crypto-Nets: Neural Networks over Encrypted Data

Pengtao Xie, Misha Bilenko, Tom Finley, Ran Gilad-Bachrach, Kristin Lauter, Michael Naehrig · 2014
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2015-01-28 · 最近 2016-11-22
2不同的人
2活跃月份
3讨论串
138被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission risk of a patient. However, due to regulations, the patient's medical files cannot be revealed. The goal is to make an inference using the model, without jeopardizing the accuracy of the prediction or the privacy of the data. To achieve high accuracy, we use neural networks, which have been shown to outperform other learning models for many tasks. To achieve the privacy requirements, we use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model. The model operates on these ciphertexts and sends back the encrypted prediction. In this protocol, not only the data remains private, even the values predicted are available only to the data owner. Using homomorphic encryption and modifications to the activation functions and training algorithms of neural networks, we show that it is protocol is possible and may be feasible. This method paves the way to build a secure cloud-based neural network prediction services without invading users' privacy.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nl · 2015-01

“If you are interested in this, the list of papers for the 2015 International Conference on Learning Representations has been released: http://www.iclr.cc/doku.php?id=iclr2015:main#submissions There's some pretty good stuff there. I really liked Crypto-Nets: Neural Networks over Encrypted Data[1]: The problem we address is the following: how can a user e…”

A Convolutional Neural Network for Modelling Sentences (2014) [pdf]原评论 ↗
评论gwern · 2016-11

“You're semi-joking, but blockchains could solve this problem cleanly: releasing secret information unless payment is made. In this case, it's a subcase of time-lock crypto (http://www.gwern.net/Self-decrypting%20files) and like time-lock crypto in general, can in theory be solved by 'witness encryption'. Witness crypto lets you create an encrypted file w…”

Nude pics as IOU: a new, risky online loan among Chinese university students原评论 ↗
被提交为 story · 1 次