Today’s world is immersed in unprecedented complexity, the deployment of convoluted networking infrastructures generates a lot of problems and challenges due to the variety of technologies used in the architectures. One of the most pressing problems lies in the inability to analyse and verify the impact of the attacks, updates and security measures in production environments. A possible solution to these situations, is the use of replicas, but the reality is that they are often not continuously updated. To address this issue, this paper presents a comprehensive framework design for securing networks by providing threat detection and security assessments of resilient services, both over Digital Twins (DTs). The solution will be able to constantly look for threats using AI-based algorithms and orchestrate the deployments of DTs in order to evaluate the possible impact of different mitigations on the network. To do so, in one of the DTs, attacks and countermeasures will be applied in different areas of the network architecture and with different time ranges. The threat impact and mitigation results will be automatically measured and analysed. With this information, new configurations will be automatically applied to the real network in order to improve network security, following an automated reactive approach.