BadVFL: Backdoor Attacks in Vertical Federated Learning

by   Mohammad Naseri, et al.

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.


page 4

page 7


Practical and General Backdoor Attacks against Vertical Federated Learning

Federated learning (FL), which aims to facilitate data collaboration acr...

Distributed and Deep Vertical Federated Learning with Big Data

In recent years, data are typically distributed in multiple organization...

Feature Inference Attack on Model Predictions in Vertical Federated Learning

Federated learning (FL) is an emerging paradigm for facilitating multipl...

Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks

Poisoning attacks are a category of adversarial machine learning threats...

Privacy Leakage of Real-World Vertical Federated Learning

Federated learning enables mutually distrusting participants to collabor...

Eavesdrop the Composition Proportion of Training Labels in Federated Learning

Federated learning (FL) has recently emerged as a new form of collaborat...

Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning

Federated learning (FL) has increasingly been deployed, in its vertical ...

Please sign up or login with your details

Forgot password? Click here to reset