Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models

Murakonda, Sasi Kumar; Shokri, Reza; Theodorakopoulos, George

doi:10.48550/arxiv.1905.12774

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on the goal of the attacker, we can classify three more attacks under the category of model inversion: membership inference, reconstruction attack, and property inference attack. Membership inference attacks (Truex et al, 2018;Hitaj et al, 2017;Murakonda et al, 2019) aim at determining whether a particular data instance was used for training. This is severe privacy issues when the instance directly maps to an identifiable individual, for instance, a medical records dataset.…”

Section: Related Workmentioning

confidence: 99%

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

Parisot¹,

Pejó²

2021

Preprint

View full text Add to dashboard Cite

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 genderwise. 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. We discuss the implication of the property inference on personal data in the light of Data Protection Regulations and Guidelines.

show abstract

Section: Related Workmentioning

confidence: 99%