Automation for Network Security Configuration: State of the Art and Research Trends

Abstract

The size and complexity of modern computer networks are progressively increasing, as a consequence of novel architectural paradigms such as the Internet of Things and network virtualization. Consequently, a manual orchestration and configuration of network security functions is no more feasible, in an environment where cyber attacks can dramatically exploit breaches related to any minimum configuration error. A new frontier is then the introduction of automation in network security configuration, i.e., automatically designing the architecture of security services and the configurations of network security functions, such as firewalls, VPN gateways, etc. This opportunity has been enabled by modern computer networks technologies, such as virtualization. In view of these considerations, the motivations for the introduction of automation in network security configuration are first introduced, alongside with the key automation enablers. Then, the current state of the art in this context is surveyed, focusing on both the achieved improvements and the current limitations. Finally, possible future trends in the field are illustrated.

A Survey of Intelligent End-to-End Networking Solutions: Integrating Graph Neural Networks and Deep Reinforcement Learning Approaches

“…Previous works supported by standardization, academia, and industry experts, are coming to conduct the creation of cutting-edge testbeds and simulation tools for network intelligence [16][17][18][19]. The motivation from existing testbeds has guided researchers towards integrating three key objectives, namely zero-touch autonomy, topology-aware scalability, and long-term efficiency, into network and service management [20,21]. In terms of these goal-oriented optimizations, graph neural networks (GNN) [22][23][24] and deep reinforcement learning (DRL) [25][26][27] are at the forefront of algorithms for advancing network automation with capabilities of extracting features and multi-aspect awareness in building controller policies.…”