From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning

A new framework named TrajSyn has been introduced to facilitate privacy-preserving dataset distillation from federated model trajectories, enabling effective server-side adversarial training without accessing raw client data. This innovation addresses the challenges posed by adversarial perturbations in deep learning models deployed on edge devices, particularly in Federated Learning settings where data privacy is paramount.

A new gradient-based membership inference attack for federated learning has been introduced, leveraging the temporal evolution of last-layer gradients across multiple federated rounds. This method does not require access to private datasets and is designed to address both semi-honest and malicious adversaries, expanding the scope of potential data leaks in federated learning scenarios.