Karl Norrman’s scientific contributions

What is this page?

This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (2)

Secure Federated Learning in 5G Mobile Networks
  • Conference Paper

December 2020

·

28 Reads

·

35 Citations

·

Karl Norrman
Fig. 1. An overview of our integration of Federated Learning (FL) in a 5G Network Data Analytics (NWDA) context.
Fig. 2. An overview of Multi-Party Computation (MPC) in Federated Learning (FL) context. In this example only two NFs are selected. The NWDAF instructs NF 1 to initiate a key exchange with all NFs with lower position, in this case only NF 0 . Following the session initialization we run an aggregation where the constructed mask m (0,1) is added by NF 0 and subtracted by NF 1 . The key K is derived from the Diffie-Hellman secret using a PRF and is part of SIGMA. A list is denoted by brackets, and a container with curly brackets.
Fig. 3. The 6 selected NFs each add masks for every other NF. The cancellation of masks m (1,2) = and m (1,4) = are indicated by the arrows. Each mask above the diagonal is canceled out by a mask below the diagonal. The cancellations of masks do not affect the aggregated sum, and 4 i=0 w * (i,t)
Secure Federated Learning in 5G Mobile Networks
  • Preprint
  • File available

April 2020

·

129 Reads

·

Karl Norrman

Machine Learning (ML) is an important enabler for optimizing, securing and managing mobile networks. This leads to increased collection and processing of data from network functions, which in turn may increase threats to sensitive end-user information. Consequently, mechanisms to reduce threats to end-user privacy are needed to take full advantage of ML. We seamlessly integrate Federated Learning (FL) into the 3GPP 5G Network Data Analytics (NWDA) architecture, and add a Multi-Party Computation (MPC) protocol for protecting the confidentiality of local updates. We evaluate the protocol and find that it has much lower overhead than previous work, without affecting ML performance.

Download

Citations (1)

... We highlight 41 general threats for 5G networks, regardless of vertical applications (Dutta and Hammad, 2020). An adversary can maliciously (1) use legitimate orchestrator access to manipulate the configuration and run a compromised network function, (2) take advantage of malicious insiders attacks, (3) perform unauthorized access (e.g., to confidential data (Isaksson and Norrman, 2020) and to RFID tags (Rahimi et al., 2018)), (4) tampering, (5) perform resource exhaustion, (6) turn services unavailable, (7) analyze or (Bordel et al., 2021)), (9) perform attacks for resource shortages, (10) extract users private information using a shared service in an unauthorized manner, (11) compromise security controls, (Vidal et al., 2018). ...

Reference:

A systematic literature mapping on the security of 5G and vertical applications
Secure Federated Learning in 5G Mobile Networks
  • Citing Conference Paper

  • December 2020

·

Karl Norrman