Secure Coded Caching with Colluding Users

Abstract: In a secure coded caching system, a central server balances the traffic flow between peak and off-peak periods by distributing some public data to the users' caches in advance. Meanwhile, these data are securely protected against the possible colluding users, who might share their cache. We model the system as a flow network and study its capacity region via a network information-theoretic approach. Due to the difficulty of characterizing the capacity region straightforwardly, our approach is two folded from the perspective of network information theory. On one hand, we identify the inner bound of capacity region by proposing a coded caching scheme to achieve a low load secure data transmission. On the other hand, we also establish outer outer bounds on the capacity region, which show that our proposed scheme is order optimal in general under specific circumstance.