18366321. MECHANISM TO ENABLE AUTHORIZATION OF NETWORK FUNCTION ACTING AS FEDERATED LEARNING CLIENTS AND FEDERATED LLEARNING SERVERS IN 5G CORE simplified abstract (Nokia Technologies Oy)
MECHANISM TO ENABLE AUTHORIZATION OF NETWORK FUNCTION ACTING AS FEDERATED LEARNING CLIENTS AND FEDERATED LLEARNING SERVERS IN 5G CORE
Organization Name
Inventor(s)
Chaitanya Aggarwal of Munich (DE)
Saurabh Khare of Bangalore (IN)
German Peindado Gomez of Warsaw (PL)
MECHANISM TO ENABLE AUTHORIZATION OF NETWORK FUNCTION ACTING AS FEDERATED LEARNING CLIENTS AND FEDERATED LLEARNING SERVERS IN 5G CORE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18366321 titled 'MECHANISM TO ENABLE AUTHORIZATION OF NETWORK FUNCTION ACTING AS FEDERATED LEARNING CLIENTS AND FEDERATED LLEARNING SERVERS IN 5G CORE
Simplified Explanation
The patent application describes a network repository function apparatus that implements an authorization mechanism for a federated learning training process.
- The apparatus includes at least one processor and at least one memory storing instructions.
- The apparatus receives FL profile data from a network data analytics function (NWDAF), including a FL process role parameter.
- It also receives an access token from the FL server for the NWDAF that is the potential FL client.
- The apparatus determines if the FL access token request is authorized for the NWDAF based on the FL profile data.
- Finally, it sends an access token for the NWDAF to the FL server when the access token request is authorized.
---
- Potential Applications
- Data analytics
- Machine learning
- Network security
- Problems Solved
- Secure authorization for federated learning processes
- Ensuring data privacy and security in FL training
- Benefits
- Improved data protection
- Enhanced network security
- Efficient authorization mechanism for FL training
Original Abstract Submitted
Various embodiments relate to network repository function apparatus configured to implement an authorization mechanism for a federated learning (FL) training process, including: at least one processor; and at least one memory storing instructions, that when executed by the at least one processor, cause the apparatus at least to: receive from a network data analytics function (NWDAF) NWDAF FL profile data including a FL process role parameter; receive an access token from the FL server for the NWDAF that is the potential FL client; determine if the FL access token request is authorized for the NWDAF based upon the FL profile data; and send an access token for the NWDAF to the FL server when access token request for the NWDAF is authorized.
