Approximate and Weighted Data Reconstruction Attack in Federated Learning

TL;DR

This paper introduces an interpolation-based approximation and weighted loss attack method that effectively reconstructs client data in federated learning, especially in the FedAvg scenario, outperforming existing techniques.

Contribution

The authors propose a novel attack method combining interpolation and layer-wise weighted loss, enabling data reconstruction in FedAvg federated learning scenarios.

Findings

The proposed AWA method outperforms state-of-the-art attacks in image data reconstruction.

Layer-wise weighting improves the quality of reconstructed data.

Experimental results demonstrate the effectiveness of the approach in various evaluation metrics.

Abstract

Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data. Although FL is considered privacy-preserved by design, recent data reconstruction attacks demonstrate that an attacker can recover clients' training data based on the parameters shared in FL. However, most existing methods fail to attack the most widely used horizontal Federated Averaging (FedAvg) scenario, where clients share model parameters after multiple local training steps. To tackle this issue, we propose an interpolation-based approximation method, which makes attacking FedAvg scenarios feasible by generating the intermediate model updates of the clients' local training processes. Then, we design a layer-wise weighted loss function to improve the data quality of reconstruction. We assign different weights to model updates in different layers concerning the neural network structure, with the weights tuned by Bayesian optimization. Finally, experimental results validate the superiority of our proposed approximate and weighted attack (AWA) method over the other state-of-the-art methods, as demonstrated by the substantial improvement in different evaluation metrics for image data reconstructions.