A Covert Queueing Channel in FCFS Schedulers

Abstract

We study covert queueing channels (CQCs), which are a kind of covert timing channel that may be exploited in shared queues across supposedly isolated users. In our system model, a user sends messages to another user via his pattern of access to the shared resource, which serves the users according to a first come first served (FCFS) policy. One example of such a channel is the cross-virtual network covert channel in data center networks, resulting from the queueing effects of the shared resource. First, we study a system comprising a transmitter and a receiver that share a deterministic and work-conserving FCFS scheduler, and we compute the capacity of this channel. We also consider the effect of the presence of other users on the information transmission rate of this channel. The achievable information transmission rates obtained in this study demonstrate the possibility of significant information leakage and great privacy threats brought by CQCs in FCFS schedulers.