The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, propomos um método de ataque seletivo de inferência de associação que determina se determinados dados correspondentes a uma classe específica estão sendo usados como dados de treinamento para um modelo de aprendizado de máquina ou não. Ao utilizar o método proposto, a adesão ou não adesão pode ser inferida gerando um modelo de decisão a partir da previsão dos modelos de inferência e treinando os valores de confiança para os dados correspondentes à classe selecionada. Usamos MNIST como conjunto de dados experimental e Tensorflow como biblioteca de aprendizado de máquina. Os resultados experimentais mostram que o método proposto tem uma taxa de sucesso de 92.4% com 5 modelos de inferência para dados correspondentes a uma classe específica.
Hyun KWON
Korea Military Academy
Yongchul KIM
Korea Military Academy
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hyun KWON, Yongchul KIM, "Toward Selective Membership Inference Attack against Deep Learning Model" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 11, pp. 1911-1915, November 2022, doi: 10.1587/transinf.2022NGL0001.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022NGL0001/_p
Copiar
@ARTICLE{e105-d_11_1911,
author={Hyun KWON, Yongchul KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Toward Selective Membership Inference Attack against Deep Learning Model},
year={2022},
volume={E105-D},
number={11},
pages={1911-1915},
abstract={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.},
keywords={},
doi={10.1587/transinf.2022NGL0001},
ISSN={1745-1361},
month={November},}
Copiar
TY - JOUR
TI - Toward Selective Membership Inference Attack against Deep Learning Model
T2 - IEICE TRANSACTIONS on Information
SP - 1911
EP - 1915
AU - Hyun KWON
AU - Yongchul KIM
PY - 2022
DO - 10.1587/transinf.2022NGL0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2022
AB - 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.
ER -