No abstract

No abstract

This paper derives upper and lower bounds on the secrecy capacity-memory tradeoff of a wiretap erasure broadcast channel (BC) with Kw weak receivers and Ks strong receivers, where weak receivers, respectively strong receivers, have same erasure probabilities and cache sizes. The lower bounds are achieved by schemes that meticulously combine joint cache-channel coding with wiretap coding and key-aided one-time pads. The presented upper bound holds more generally for arbitrary degraded BCs and arbitrary cache sizes. When only weak receivers have cache memories, upper and lower bounds coincide for small and large cache memories, thus providing the exact secrecy capacity-memory tradeoff for this setup. The derived bounds allow to further conclude that the secrecy capacity is positive even when the eavesdropper is stronger than all the legitimate receivers with cache memories. Moreover, they show that the secrecy capacity-memory tradeoff can be significantly smaller than its non-secure counterpart, but it grows much faster when cache memories are small.The paper also presents a lower bound on the global secrecy capacity-memory tradeoff where one is allowed to optimize the cache assignment subject to a total cache budget. It is close to the best known lower bound without secrecy constraint. For small total cache budget, the global secrecy capacity-memory tradeoff is achieved by assigning all the available cache memory uniformly over all receivers if the eavesdropper is stronger than all legitimate receivers, and it is achieved by assigning the cache memory uniformly only over the weak receivers if the eavesdropper is weaker than the strong receivers.The slope γ of the standard non-secure capacity-memory tradeoff satisfies (see [2, Theorem 2])This latter slope γ thus deteriorates with increasing library size D, which is not the case for γ sec . The main reason for this behavior is that in a standard system the cache memories are filled with data, and intuitively each stored bit is useful only under some of the demands. In a secure system, a good option is to store secret keys in the cache memories of the receivers. These secret keys are helpful for all possible demands, and therefore the caching gain does not degrade with the library size D.• Optimal Cache Assignments for Small Total Cache Budgets: For small total cache budgets, the global secrecy capacitymemory tradeoff is achieved by assigning all of the cache memory uniformly only over the weak receivers if the Library W