Non-Linear Trajectory Modeling for Multi-Step Gradient Inversion Attacks in Federated Learning
This work addresses privacy vulnerabilities in federated learning for multi-step scenarios, offering insights for defense strategies, though it is incremental as it builds on existing surrogate model methods.
The paper tackled the problem of gradient inversion attacks in federated learning by proposing NL-SME, a method that models nonlinear parameter trajectories, which achieved order-of-magnitude improvements in cosine similarity loss on datasets like CIFAR-100 and FEMNIST.
Federated Learning (FL) preserves privacy by keeping raw data local, yet Gradient Inversion Attacks (GIAs) pose significant threats. In FedAVG multi-step scenarios, attackers observe only aggregated gradients, making data reconstruction challenging. Existing surrogate model methods like SME assume linear parameter trajectories, but we demonstrate this severely underestimates SGD's nonlinear complexity, fundamentally limiting attack effectiveness. We propose Non-Linear Surrogate Model Extension (NL-SME), the first method to introduce nonlinear parametric trajectory modeling for GIAs. Our approach replaces linear interpolation with learnable quadratic Bézier curves that capture SGD's curved characteristics through control points, combined with regularization and dvec scaling mechanisms for enhanced expressiveness. Extensive experiments on CIFAR-100 and FEMNIST datasets show NL-SME significantly outperforms baselines across all metrics, achieving order-of-magnitude improvements in cosine similarity loss while maintaining computational efficiency.This work exposes heightened privacy vulnerabilities in FL's multi-step update paradigm and offers novel perspectives for developing robust defense strategies.