defense arXiv Jan 9, 2025 · Jan 2025
Guannan Lai, Yihui Feng, Xin Yang et al. · Southwestern University of Finance and Economics · Chongqing University of Posts and Telecommunications +1 more
Defends federated learning against gradient reconstruction attacks by transforming images into coarse-grained graph structures before training
Model Inversion Attack visionfederated-learninggraph
Federated Learning (FL) facilitates collaborative model training while prioritizing privacy by avoiding direct data sharing. However, most existing articles attempt to address challenges within the model's internal parameters and corresponding outputs, while neglecting to solve them at the input level. To address this gap, we propose a novel framework called Granular-Ball Federated Learning (GrBFL) for image classification. GrBFL diverges from traditional methods that rely on the finest-grained input data. Instead, it segments images into multiple regions with optimal coarse granularity, which are then reconstructed into a graph structure. We designed a two-dimensional binary search segmentation algorithm based on variance constraints for GrBFL, which effectively removes redundant information while preserving key representative features. Extensive theoretical analysis and experiments demonstrate that GrBFL not only safeguards privacy and enhances efficiency but also maintains robust utility, consistently outperforming other state-of-the-art FL methods. The code is available at https://github.com/AIGNLAI/GrBFL.
gnn federated cnn Southwestern University of Finance and Economics · Chongqing University of Posts and Telecommunications · Southwest Jiaotong University
ML Security Papers