Decentralized Learning for 6G Security: Open Issues and Future Directions
Janani Kehelwala, Yushan Siriwardhana, Tharaka Mawanane Hewa, Madhusanka Liyanage, Mika Ylianttila · 2024
6G is envisioned with stringent performance requirements served using an open and hyper-dynamic architecture where intelligence is embedded across multiple logical layers. Artificial Intelligence (AI), a key enabling technology in implementing this vision, is often proposed in a centralized mode of operation that does not serve the scalability and fault tolerance required for the self-sustainability objectives of 6G. This paper conceptualizes decentralized learning as an alternative enabling technology for 6G, suited for highly dynamic orchestration and serving fault-tolerance and scalability objectives alongside additional security and privacy prospects. Our contributions include establishing the decentralization-oriented altered threat land-scape, identifying open issues in current solutions, and defining future research directions to ensure a robust 6G infrastructure.