JSAI2022

Presentation information

General Session

General Session » GS-11 AI and Society

[1D5-GS-11] AI and Society

Tue. Jun 14, 2022 4:20 PM - 5:40 PM Room D (Room D)

座長:藤井 慶輔(名古屋大学)[遠隔]

4:20 PM - 4:40 PM

[1D5-GS-11-01] Avoiding Privacy Data Exposure in Machine Learning Models with Differential Privacy

〇Fumiya Komatsu1, Takashi Takekawa1 (1. Kogakuin University of Technology and Engineering)

Keywords:Differential Privacy, Privacy Preserving, Machine Learning

In recent years, machine learning has made it possible to utilize various types of data. On the other hand, as the opportunities to use data increase, data breach from machine learning models has been pointed out. For example, consider a model that provides input candidates while writing an e-mail. If this model outputs a credit card number that exists in the training data, this is a data breach. In this research, as a countermeasure against data breach, we tackled the task of text generation by RNN using DP-Adam, an optimization algorithm that satisfies differential privacy. We tested whether it is possible to prevent the exposure of dummy data, which is assumed to be personal information. As a result, we confirmed that the DP-Adam model and the L1-regularized model avoided the dummy data exposure. However, the text generated by the L1-regularized model contained words that did not exist.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password