Approximate and Weighted Data Reconstruction Attack in Federated Learning
This work addresses privacy vulnerabilities in federated learning for users and organizations, but it is incremental as it builds on prior attack methods.
The paper tackles the challenge of data reconstruction attacks in horizontal Federated Averaging (FedAvg) scenarios, where existing methods often fail, by proposing an interpolation-based approximation method and a layer-wise weighted loss function, resulting in substantial improvements in image data reconstruction metrics.
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.