Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model’s Complexity

Mathias Parisot, Balázs Pejó, Dayana Spagnuelo

2021

Abstract

Machine learning models’ goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task. Property Inference Attacks exploit this and aim to infer from a given model (i.e., the target model) properties about the training dataset seemingly unrelated to the model’s primary goal. If the training data is sensitive, such an attack could lead to privacy leakage. In this paper, we investigate the influence of the target model’s complexity on the accuracy of this type of attack, focusing on convolutional neural network classifiers. We perform attacks on models that are trained on facial images to predict whether someone’s mouth is open. Our attacks’ goal is to infer whether the training dataset is balanced gender-wise. Our findings reveal that the risk of a privacy breach is present independently of the target model’s complexity: for all studied architectures, the attack’s accuracy is clearly over the baseline.

Paper Citation

in Harvard Style

Parisot M., Pejó B. and Spagnuelo D. (2021). Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model’s Complexity. In Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT, ISBN 978-989-758-524-1, pages 715-721. DOI: 10.5220/0010555607150721

in Bibtex Style

@conference{secrypt21,
author={Mathias Parisot and Balázs Pejó and Dayana Spagnuelo},
title={Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model’s Complexity},
booktitle={Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT,},
year={2021},
pages={715-721},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010555607150721},
isbn={978-989-758-524-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT,
TI - Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model’s Complexity
SN - 978-989-758-524-1
AU - Parisot M.
AU - Pejó B.
AU - Spagnuelo D.
PY - 2021
SP - 715
EP - 721
DO - 10.5220/0010555607150721