Federated Learning for Offensive Security in Cyber-Medical Systems Inspired by Petri Nets

Federated learning is a machine learning method that allows models to be trained on decentralised data without participants sharing it with a central server. Federated learning can be modelled using Petri nets, mathematical models for sequence sequences. Devices train on their own data and send model updates to a central server. The central server averages the updates and returns the global model to the devices. The devices then update their local models using the global model.