Threat Modeling of AI-as-a-Service Framework

Artificial intelligence will be one of the key enablers of 6G technology. Compared to today's networks where we mostly benefit from ubiquitous communication capabilities, 6G is expected to transform the network into a powerfully distributed AI platform and exposes its AI capabilities to consumers. This is expected to be enabled by the AI-as-a-Service (AIaaS) framework. The latter unlocks new possibilities for network management and orchestration in the context of 6G by enabling network service providers to leverage AI capabilities as a service effectively. Thus, it is extremely important for the AIaaS framework to be intelligently protected against potential threats and malicious attacks. In this paper, we performed a comprehensive threat analysis of the AIaaS framework, identifying potential security threats and discussing mitigation strategies.