Learning Autonomic Security Reconfiguration Policies

The authors explore the idea of applying machine learning techniques to automatically infer risk-adaptive policies to reconfigure a network security architecture when the context in which it operates changes. To illustrate their approach, they consider the case of a MANET where nodes carrying sensitive services (e.g., web servers, key repositories, etc.) should consider relocating themselves into a different node to guarantee proper functioning. They use simulation to derive properties from a candidate policy, and then apply Genetic Programming and Multi-Objective Optimisation techniques to search for optimal candidates.