Privacy Against Inference Attacks in Vertical Federated Learning

  title={Privacy Against Inference Attacks in Vertical Federated Learning},
  author={Borzoo Rassouli and Morteza Varasteh and Deniz G{\"u}nd{\"u}z},
Vertical federated learning is considered, where an active party, having access to true class labels, wishes to build a classification model by utilizing more features from a passive party, which has no access to the labels, to improve the model accuracy. In the prediction phase, with logistic regression as the classification model, several inference attack techniques are proposed that the adversary, i.e., the active party, can employ to reconstruct the passive party’s features, regarded as… 



Comprehensive Analysis of Privacy Leakage in Vertical Federated Learning During Prediction

A comprehensive analysis of privacy leakage in VFL frameworks during the prediction phase is conducted and a general gradient-based reconstruction attack framework is designed that can be flexibly applied to simple logistic regression models as well as multi-layer neural networks.

Feature Inference Attack on Model Predictions in Vertical Federated Learning

This paper presents several feature inference attack methods to investigate the potential privacy leakages in the model prediction stage of vertical FL and proposes two specific attacks on the logistic regression (LR) and decision tree (DT) models, according to individual prediction output.

A trusted recommendation scheme for privacy protection based on federated learning

A collaborative filtering algorithm recommendation system based on federated learning on end-edge-cloud based on protection of data privacy and the training model and recommendation information is stored to the blockchain network to provide permanent storage, evidence chain and real-time traceability services.

A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression

This paper proposes a quasi-Newton method based vertical federated learning framework for logistic regression under the additively homomorphic encryption scheme and can considerably reduce the number of communication rounds with a little additional communication cost per round.

Communication-Efficient Learning of Deep Networks from Decentralized Data

This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

Privacy-preserving Federated Brain Tumour Segmentation

The feasibility of applying differential-privacy techniques to protect the patient data in a federated learning setup for brain tumour segmentation on the BraTS dataset is investigated and there is a trade-off between model performance and privacy protection costs.

Protocols for secure computations

  • A. Yao
  • Mathematics
    23rd Annual Symposium on Foundations of Computer Science (sfcs 1982)
  • 1982
The author gives a precise formulation of this general problem and describes three ways of solving it by use of one-way functions, which have applications to secret voting, private querying of database, oblivious negotiation, playing mental poker, etc.

Toward Resource-Efficient Federated Learning in Mobile Edge Computing

A neural-structure-aware resource management approach with mod-ule-based federated learning is proposed, where mobile clients are assigned with different subnetworks of the global model according to the status of their local resources.

A Generalisation, a Simplification and Some Applications of Paillier's Probabilistic Public-Key System

We propose a generalisation of Paillier's probabilistic public key system, in which the expansion factor is reduced and which allows to adjust the block length of the scheme even after the public key

Data-Snooping Biases in Tests of Financial Asset Pricing Models

We investigate the extent to which tests of financial asset pricing models may be biased by using properties of the data to construct the test statistics. Specifically, we focus on tests using