Afficher la couverture 'Membership Inference Attacks via Adversarial Examples | Jalalzai, Hamid' en grand format
/5

0 avis

Membership Inference Attacks via Adversarial Examples

Archive ouverte

Jalalzai, Hamid | Kadoche, Elie | Leluc, Rémi | Plassier, Vincent

Edité par CCSD -

Trustworthy and Socially Responsible Machine Learning (TSRML 2022) co-located with NeurIPS 2022. The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often include personal data which can represent a threat to privacy. Membership inference attacks are a novel direction of research which aims at recovering training data used by a learning algorithm. In this paper, we develop a mean to measure the leakage of training data leveraging a quantity appearing as a proxy of the total variation of a trained model near its training samples. We extend our work by providing a novel defense mechanism. Our contributions are supported by empirical evidence through convincing numerical experiments.

Consulter en ligne

Suggestions

Du même auteur

Feature Clustering for Support Identification in Extreme Regions

Archive ouverte | Jalalzai, Hamid | CCSD

International audience. Understanding the complex structure of multivariate extremes is a major challenge in various fields from portfolio monitoring and environmental risk management to insurance. In the framework ...

Distributed Monte Carlo simulation with large-scale Machine Learning : Bayesian Inference and Conformal Prediction. Simulation de Monte Carlo distribuée avec apprentissage statistique à grande échelle : Inférence bayésienne et prédiction conformelle

Archive ouverte | Plassier, Vincent | CCSD

Centralizing data is impractical or undesirable in many scenarios, especially when sensitive information is involved. In such cases, the need for alternative methods becomes evident. As large datasets are known to facilitate the l...

QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning

Archive ouverte | Vono, Maxime | CCSD

International audience. The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients. FL raises many constraints which include...

Chargement des enrichissements...