The search functionality is under construction.
The search functionality is under construction.

Toward Selective Membership Inference Attack against Deep Learning Model

Hyun KWON, Yongchul KIM

  • Full Text Views

    0

  • Cite this

Summary :

In this paper, we propose a selective membership inference attack method that determines whether certain data corresponding to a specific class are being used as training data for a machine learning model or not. By using the proposed method, membership or non-membership can be inferred by generating a decision model from the prediction of the inference models and training the confidence values for the data corresponding to the selected class. We used MNIST as an experimental dataset and Tensorflow as a machine learning library. Experimental results show that the proposed method has a 92.4% success rate with 5 inference models for data corresponding to a specific class.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.11 pp.1911-1915
Publication Date
2022/11/01
Publicized
2022/07/26
Online ISSN
1745-1361
DOI
10.1587/transinf.2022NGL0001
Type of Manuscript
Special Section LETTER (Special Section on Next-generation Security Applications and Practice)
Category

Authors

Hyun KWON
  Korea Military Academy
Yongchul KIM
  Korea Military Academy

Keyword