Exploring Potential Vulnerabilities in Decomposed Convolutional Filters for Federated Learning
Federated Learning (FL) enables collaborative model training across distributed clients without directly sharing sensitive local data. However, the sharing of gradients or model updates still leaves the framework vulnerable to privacy breaches, notably Deep Leakage from Gradients (DLG). To counter such threats, recent methodologies like Decomposed Convolutional Filters (DCF) have been proposed. DCF attempts to mask the true gradients by decomposing convolution weights into Filter Atoms and Shared Atom Coefficients, exchanging only the Filter Atoms. In this paper, we explore a potential vulnerability in the DCF-based FL architecture. We provide a threat model and an attack scenario demonstrating how an honest-but-curious server could mathematically reconstruct a client’s local model. By evaluating the intermediate stage of the attack under various initialization and training scenarios, we provide empirical evidence that DCF inherently suffers from a critical trade-off between model utility and structural leakage, enabling potential data reconstruction.