BadVFL: Backdoor Attacks in Vertical Federated Learning - INRIA 2 Access content directly
Conference Papers Year : 2024

BadVFL: Backdoor Attacks in Vertical Federated Learning

Abstract

Federated learning (FL) enables multiple parties to collaboratively train a machine learning model without sharing their data; rather, they train their own model locally and send updates to a central server for aggregation. Depending on how the data is distributed among the participants, FL can be classified into Horizontal (HFL) and Vertical (VFL). In VFL, the participants share the same set of training instances but only host a different and non-overlapping subset of the whole feature space. Whereas in HFL, each participant shares the same set of features while the training set is split into locally owned training data subsets. VFL is increasingly used in applications like financial fraud detection; nonetheless, very little work has analyzed its security. In this paper, we focus on robustness in VFL, in particular, on backdoor attacks, whereby an adversary attempts to manipulate the aggregate model during the training process to trigger misclassifications. Performing backdoor attacks in VFL is more challenging than in HFL, as the adversary i) does not have access to the labels during training and ii) cannot change the labels as she only has access to the feature embeddings. We present a first-of-its-kind clean-label backdoor attack in VFL, which consists of two phases: a label inference and a backdoor phase. We demonstrate the effectiveness of the attack on three different datasets, investigate the factors involved in its success, and discuss countermeasures to mitigate its impact.
Fichier principal
Vignette du fichier
313000a008.pdf (597.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
licence : Public Domain

Dates and versions

hal-04321905 , version 1 (04-12-2023)

Licence

Attribution

Identifiers

  • HAL Id : hal-04321905 , version 1

Cite

Mohammad Naseri, Yufei Han, Emiliano de Cristofaro. BadVFL: Backdoor Attacks in Vertical Federated Learning. SP 2024 - IEEE Symposium on Security and Privacy, May 2024, San Francisco, United States. pp.1-8. ⟨hal-04321905⟩
154 View
18 Download

Share

Gmail Facebook X LinkedIn More