Sequences of millions of bytes are ubiquitous; for example, music, image, or video files typically consist of multiple megabytes.

Federated Learning (FL) allows machine learning models to train locally on individual mobile devices, synchronizing model updates via a shared server.

To mitigate the negative effect of data heterogeneity (non-IIDness), two common approaches are clustering and personalization.

Due to its distributed nature, many studies have shown that it is vulnerable to backdoor attacks.

Federated Learning (FL) is an emerging collaborative machine learning framework where multiple clients train the global model without sharing their own datasets.

To bridge this gap, we model the strategic interactions between the defender and dynamic attackers as a minimax game. Based on the analysis of the game, we design an interactive defense mechanism FedGame. We prove that under mild assumptions, the global model trained with FedGame under backdoor attacks is close to that trained without attacks.