A nature-inspired decision system for secure cyber network architecture
Neal Wagner, Cem Şahin, Jaime Peña, William Streilein · 2017
Cyber security experts have recommended splitting a computer network into multiple segments to limit the damage that an attacker can cause after penetrating the network. However, there is no clear guidance on what segmentation architectures are best to maximize a network's security posture. Furthermore, modern networks are complex and vary widely from organization to organization and, thus, there exists no single “best” architecture that will maximize security for all network environments. Hence, security practitioners rely on judgment to determine which architecture is best for their network. This paper proposes a cyber decision support system that automatically generates security-optimized segmentation architectures for network environments subject to dynamically-changing cyber threats. The system employs a hybrid approach that combines nature-inspired optimization methods with simulation modeling to construct and evaluate candidate architectures, intelligently search the space of possible architectures, and adapt to changing threat levels. We demonstrate the system via a case study on a representative network environment under an evolving cyber attack.