Trustworthy Analytics in ETSI ZSM: A 5G Security Case Study

Towards the advent of the sixth generation (6G) wireless networks, smart technologies play a key role in the end-to-end automation of services across multiple domains. In particular, they create a new reality with multiple benefits, including intent-driven management, ultra-speed communication services and holistic integration within the Internet of Things (IoT). In this context, the Zero-touch Network and Service Management (ZSM) group within the European Telecommunications Standards Institute (ETSI) aims to provide an architectural framework which will allow the zero-touch orchestration of network services in a multi-domain fashion. Therefore, in this paper, we investigate the role of cross-domain storage, communication and analytics services within the architectural framework of ETSI ZSM. For this purpose, we take into account a particular case study which focuses on the orchestration of security services within the 5G core. More specifically, the deployment of a new User Plane Function (UPF) equipped with intrusion detection services that leverage Artificial Intelligence (AI) is investigated. For this purpose, the aforementioned cross-domain services are used to assess the security of the respective AI models before the onboarding of the new UPF within the 5G core. Based on this case study, a new security game is investigated, exploring and modelling the strategies of potential attackers and defenders. Furthermore, the architectural design and implementation of the cross-domain services are provided. Finally, the evaluation results show that the cross-domain analytics services are able to assess the security and resilience of the AI models and guide the orchestration functions.