Research Area: Software Defined Networks
Software-defined networking (SDN) utilizes a centralized controller to distribute packet processing rules to network switches. However, rules are often generated by the applications developed by different organizations, so they may conflict with each other in data plane and lead to violations with security rules. The problem is similar to firewall conflicts in IP networks. Rule conflict resolution should incur negligible process delay, such that all rules can be correctly and safely enforced in the data plane in real time. However, since SDN allows users to use more than 35 fields to specify rules (including field transition rules), it is much more complicated to prevent enforcement of SDN rules from violating with security rules than to resolve firewall rule violation, and in particular, field transition rules are enforced. Therefore, it is extremely difficult to resolve such rule conflicts in real time before the rules are installed in SDN data plane. In this paper, we investigate the rule conflict problem in SDN and identify new covert channel attacks due to rule conflicts. To the end, we propose the covert channel defender (CCD) that prevents covert channel attacks by verifying and resolving rule conflicts. Specifically, CCD tracks all rule insertion and modification messages from applications running on the controller. It analyzes the correlation among rules based on multiple packet header fields and resolves any identified rule conflict in real time before rule installation. We implement CCD with the Floodlight controller and evaluate its performance with the real-world Stanford topology. We show that CCD can efficiently detect and prevent rule conflicts in the data plane that may raise covert channels within hundreds of microseconds and brings small overhead to the packet delivery.
Keywords:
SDN
data plane
policy violation
Author(s) Name: Qi Li; Yanyu Chen; Patrick P. C. Lee; Mingwei Xu; Kui Ren
Journal name: IEEE/ACM Transactions on Networking
Conferrence name:
Publisher name: IEEE
DOI: 10.1109/TNET.2018.2853593
Volume Information: Volume: 26, Issue: 4, August 2018, Page(s): 1715 - 1727
