Research Article

Balancing Data Privacy and 5G VNFs Security Monitoring: Federated Learning with CNN + BiLSTM + LSTM Model

Algorithm 1

Federated averaging learning procedure with TLS encryption.
Input: number of rounds T, number of local epochs E, and number of participating clients N
Output: final global model W after T rounds of federated learning
(1)Initialize: Global model ;
(2)for t = 1 to T do
(3)for i = 1 to N do
(4)  Establish a secure TLS connection between the client and the server;
(5)  Retrieve local data and associated labels
(6)  Initialize: Local model parameters  = ;
(7)  for e = 1 to E do
(8)   Update using and through local training;
(9)  end
(10)  Securely send the updated local model to the server using the established TLS connection;
(11)end
(12) Aggregate and update the global model using the received local models;
(13) Send the updated global model to all participating clients using the TLS connection;
(14)end