The price of safety in an active network

Security is a major challenge for "Active Networking," as accessible programmability creates numerous opportunities for mischief. The point at which programmability is exposed, e.g., through the loading and execution of code in network elements, must therefore be carefully crafted to ensure security. The SwitchWare active networking research project has studied the architectural implications of various tradeoffs between performance and security. Namespace protection and type safety were achieved with a module loader for active networks, ALIEN, which carefully delineated boundaries for privilege and dynamic updates. ALIEN supports two extensions, the Secure Active Network Environment (SANE), and the Resource Controlled Active Network Environment (RCANE). SANE extends ALIEN's node protection model into a distributed setting, and uses a secure bootstrap to guarantee integrity of the namespace protection system. RCANE provides resource isolation between active network node users, including separate heaps and robust time-division multiplexing of the node. The SANE and RCANE systems show that convincing active network security can be achieved. This paper contributes a measurement-based analysis of the costs of such security with an analysis of each system based on both execution traces and end-to-end behavior.