paper-with-me

Papers

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

2021-04-27 · Mathias P. M. Parisot, Balazs Pejo, Dayana Spagnuelo

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 (\ie 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. This paper investigates 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. We discuss the implication of the property inference on personal data in the light of Data Protection Regulations and Guidelines.

📄 PDF Abstract BibTeX arXiv:2104.13061

Code (1)

matprst/pia-on-cnn pytorch

Similar Papers 제목 키워드 기반

SNAP: Efficient Extraction of Private Properties with Poisoning

2022-08-25 · Harsh Chaudhari, John Abascal, Alina Oprea, Matthew Jagielski 외

Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. Such attacks have privacy implications for data owners sharing their datasets to train mac…

Inference Attack

Formalizing Distribution Inference Risks

2021-06-07 · Anshuman Suri, David Evans

Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the primary purposes of statistical machine learning, which is to produce models that capture statistica…

Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications

2021-10-17 · Bang Wu, Xiangwen Yang, Shirui Pan, Xingliang Yuan

Graph Neural Networks (GNNs) are widely adopted to analyse non-Euclidean data, such as chemical networks, brain networks, and social networks, modelling complex relationships and interdependency between objects. Recently…

Graph ClassificationInference AttackMembership Inference Attack

Property Inference Attacks Against GANs

2021-11-15 · Junhao Zhou, Yufei Chen, Chao Shen, Yang Zhang

While machine learning (ML) has made tremendous progress during the past decade, recent research has shown that ML models are vulnerable to various security and privacy attacks. So far, most of the attacks in this field …

AttributeFairnessInference Attack

Alignment Defends LLMs from Property Inference Attacks

2026-06-08 · Pengrun Huang, Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri arxiv

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-level information can be effectively extr…