Training of classification models via federated learning and homomorphic encryption

HIGHLIGHTS

• who: Eduardo Angulo and colleagues from the Department of Computer Science and Engineering, Universidad del Norte, Barranquilla, Colombia have published the article: Training of Classification Models via Federated Learning and Homomorphic Encryption, in the Journal: Sensors 2023, 23, 1966. of /2023/
• what: This work proposed a cryptographic protocol to train MLP neural_networks by combining federated learning and homomorphic encryption. Concerning the privacy guarantees, the analysis shows that the proposed protocol strives to preserve data privacy through the secure aggregation method based on homomorphic encryption since it prevents information leakage from client gradients.
• how . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.