Group rekeying with limited unicast recovery q

In secure group communications, a key server can deliver a ‘‘group-oriented’’ rekey message [C.K. Wong, M.G. Gouda, S.S. Lam, Secure group communications using key graphs, in: Proceedings of ACM SIGCOMM 98, September 1998, pp. 68–79] to a large number of users efficiently using multicast. For reliable delivery, Keystone [C.K. Wong, S.S. Lam, Keystone: a group key management system, in: Proceedings of International Conference on Telecommunications, Acapulco, Mexico, May 2000] proposed the use of forward error correction (FEC) in an initial multicast, followed by the use of unicast delivery for users that cannot recover their new keys from the multicast. In this paper, we investigate how to limit unicast recovery to a small fraction r of the user population. By specifying a very small r, almost all users in the group will receive their new keys within a single multicast round. We present analytic models for deriving r as a function of the amount of FEC redundant information (denoted by h) and the rekeying interval duration (denoted by T ) for both Bernoulli and two-state Markov Chain loss models. From our analyses, we conclude that r decreases roughly at an exponential rate as h increases. We then present a protocol designed to adaptively adjust ðh; T Þ to achieve a specified r. In particular, our protocol chooses from among all feasible ðh; T Þ pairs one with h and T values close to their feasible minima. Our protocol also adapts to an increase in network traffic. Simulation results using ns-2 show that with network congestion our adaptive FEC protocol can still achieve a specified r by adjusting values of h and T . 2003 Elsevier B.V. All rights reserved. Research sponsored by NSF grants ANI-9977267 and ANI-0319168, and Texas Advanced Research Program 0036580439-2001. An abbreviated version of this paper appeared in Proceedings of ICC 2003 Symposium on Next Generation Internet, Anchorage, AK, May 2003. * Corresponding author. Tel.: +1-512-4719531; fax: +1-512-