6G Cure: Robust threat prevention for AI/ML for beyond 5G and 6G

6G Cure

6G Cure is Business Finland funded project that develops robust techniques to prevent selected AI/ML learning systems from poisoning and inference attacks, focusing especially on beyond 5G and 6G networks
6G Cure project

Project information

Project duration

-

Funded by

Business Finland

Project funder

Business Finland
WithSecure (Finland)
Nokia Bell Labs (Finland)
Silo.AI
Traficom
ETRI, Korea
Telefonica
University College Dublin

Funding amount

553 000 EUR

Project coordinator

University of Oulu

Contact information

Project leader

Other persons

Project description

5G Advanced and 6G networks and systems will include an increased amount of distributed ML/AI algorithms implemented to various network functions both in radio access and core networks. The used algorithms may not be designed to be robust against certain types of attacks such as model poisoning and inference attacks. Poisoning attacks launched by adversaries focus on decreasing the quality of the AI/ML models while inference attacks try to reconstruct the data that the AI/ML algorithms were trained. These kinds of attacks can decrease the system performance regarding the KPIs, and may also result in increased system downtime and service unavailability in critical applications.

The 6G Cure project proposes robust techniques for Machine Learning (ML), that eliminate the adversaries in the local network and provides early detection, prevention, and mitigation of poisoning attacks and membership inference attacks on decentralized ML models. Proposed robust algorithms consider different architectures of learning networks, remove the malicious model updates received from the peer users and consider only the legitimate update to continue the learning process. When the data is not visible to peers in decentralized learning, only the properties of the model update can be used to identify the malicious nodes in the system. In “Gossip Learning”, partial model updates may be shared to minimize the risk of membership inference attacks. This makes the implementation of robust algorithms even more challenging in the presence of poisoning and membership inference attacks as the defender has less data for the analysis.

These robust techniques are applicable in various 5G Advanced and 6G use cases including Unmanned Aerial Vehicle (UAV) networks, self-driving cars, critical medical and industrial applications, and automated network management. The proposed solutions can be implemented for example as part of advanced network slicing solutions in 5G Advanced and 6G.

Project results

International peer-reviewed conference proceedings and demos

  1. Y. Siriwardhana, P. Porambage, M. Liyanage, S. Marchal, M. Ylianttila, "Robust Aggregation Technique Against Poisoning Attacks in Multi-Stage Federated Learning Applications", accepted to 2024 IEEE Consumer Communications and Networking Conference (CCNC), Las Vegas, USA.
  2. J. Kehelwala, Y. Siriwardhana, T. Hewa, M. Ylianttila, "Defending against poisoning attacks in Federated Learning systems in autonomous driving", Brooklyn 6G Summit, B6GS 2023 – Demo.
  3. T. Hewa, P. Porambage, M. Liyanage, M. Ylianttila," Towards Attack Resistant Federated Learning with Blockchain in 5G and Beyond Networks", 2023 EuCNC & 6G Summit - Posters.

Datasets

  1. S. Samarakoon, Y. Siriwardhana, P. Porambage, M. Liyanage, S. Chang, Jinoh Kim, Jonghyun Kim, M. Ylianttila, "5G-NIDD: A Comprehensive Network Intrusion Detection Dataset Generated over 5G Wireless Network". arXiv:2212.01298 [cs.CR],https://doi.org/10.48550/arXiv.2212.01298 (Pre-print of ongoing work)