| Title | Feature Inference Attack on Model Predictions in Vertical Federated Learning |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Luo, Xinjian, Wu, Yuncheng, Xiao, Xiaokui, Ooi, Beng Chin |
| Conference Name | 2021 IEEE 37th International Conference on Data Engineering (ICDE) |
| Keywords | Adversary Models, Collaborative Work, Data models, data privacy, feature inference attack, Human Behavior, Metrics, model prediction, Organizations, Prediction algorithms, Predictive models, privacy preservation, pubcrawl, Radio frequency, Resiliency, Scalability, vertical federated learning |
| Abstract | Federated learning (FL) is an emerging paradigm for facilitating multiple organizations' data collaboration without revealing their private data to each other. Recently, vertical FL, where the participating organizations hold the same set of samples but with disjoint features and only one organization owns the labels, has received increased attention. This paper presents several feature inference attack methods to investigate the potential privacy leakages in the model prediction stage of vertical FL. The attack methods consider the most stringent setting that the adversary controls only the trained vertical FL model and the model predictions, relying on no background information of the attack target's data distribution. We first propose two specific attacks on the logistic regression (LR) and decision tree (DT) models, according to individual prediction output. We further design a general attack method based on multiple prediction outputs accumulated by the adversary to handle complex models, such as neural networks (NN) and random forest (RF) models. Experimental evaluations demonstrate the effectiveness of the proposed attacks and highlight the need for designing private mechanisms to protect the prediction outputs in vertical FL. |
| DOI | 10.1109/ICDE51399.2021.00023 |
| Citation Key | luo_feature_2021 |
Feature Inference Attack on Model Predictions in Vertical Federated Learning