Efficient passive membership inference attack in federated learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Efficient passive membership inference attack in federated learning

Abstract

In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information can still be disclosed to an adversary who just eavesdrops the messages exchanged between the client and the server. For example, the adversary can infer whether the client owns a specific data instance, which is called a passive membership inference attack. In this paper, we propose a new passive inference attack that requires much less computation power and memory than existing methods. Our empirical results show that our attack achieves a higher accuracy on CIFAR100 dataset (more than 4 percentage points) with three orders of magnitude less memory space and five orders of magnitude less calculations.
Fichier principal
Vignette du fichier
Passive_inference_attack(2).pdf (522.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03410152 , version 1 (31-10-2021)

Identifiers

Cite

Oualid Zari, Chuan Xu, Giovanni Neglia. Efficient passive membership inference attack in federated learning. NeurIPS PriML 2021 - workshop Privacy in Machine Learning, Dec 2021, Virtual, France. ⟨hal-03410152⟩
100 View
136 Download

Altmetric

Share

Gmail Facebook X LinkedIn More