Search

A software-defined network (SDN) is increasingly deployed in many practical settings, bringing new security risks, e.g., SDN controller and switch hijacking. In this paper, we propose a real-time method to detect compromised SDN devices in a reliable way. The proposed method aims at solving the detection problem of compromised SDN devices when both the controller and the switch are trustless, and it is complementary with existing detection methods. Our primary idea is to employ backup controllers to audit the handling information of network update events collected from the primary controller and its switches, and to detect compromised devices by recognizing inconsistent or unexpected handling behaviors among the primary controller, backup controllers, and switches. Following this idea, we first capture each network update request and its execution result in the primary controller, collect each received network update instruction and the information of any state update in switches, and deliver these four kinds of information to those backup controllers in an auditor role. An auditor controller is designed to create an audit record for each received network update request and to add its execution result of this network update request as well as the received four kinds of matching information to the audit record. In particular, heterogeneous auditor controllers are proposed to avoid the same vulnerability with the primary controller. The audit algorithm and theoretical proof of its effectiveness for security enhancement are then presented. Finally, based on our prototype implementation, our experimental results further validate the proposed method and its low costs. [ABSTRACT FROM AUTHOR]

Maintaining service availability during an inter-domain route update is a challenge in both conventional networks and software-defined networks (SDNs). In the update process, asynchronous reconfigurations to border forwarding devices in different domains will incur transient anomalies with numerous packet losses and service disruptions. Based on current SDN inter-domain routing mechanisms, we in this paper propose a lossless and seamless method for SDN inter-domain route updates. This method is lightweight, and it has no requirement to add extra switch functionality or to extend SDN southbound protocols. The primary idea of this method is to achieve a lossless inter-domain route update by communications and collaborations among relevant domains. Motivated by this idea, we first identify three different domain categories for the update, i.e., domains only on the new inter-domain route, domains on both the old and new inter-domain routes, and domains only on the old inter-domain route. We further find that the transient anomalies are able to be avoided by reconfiguring the related border switches of the three categories of domains in order. Four update steps are then designed to keep the orderly update. Furthermore, we present the theoretical proof of the effectiveness of this method. Finally, based on our prototype implementation, the proposed method is also validated by simulation studies, and the simulation results indicate that this method succeeds in avoiding packet loss and maintaining service availability during the update. [ABSTRACT FROM AUTHOR]