Guarding 6G use cases: a deep dive into AI/ML threats in All-Senses meeting

Abstract

With the recent advances in 5G and 6G communications and the increasing need for immersive interactions due to pandemic, new use cases such as All-Senses meeting are emerging. To realize these use cases, numerous sensors, actuators, and virtual reality devices are used. Additionally, artificial intelligence (AI) and machine learning (ML) including generative AI can be used to analyze large amount of data generated by 6G networks and devices to enable new applications and services. While AI/ML technologies are evolving, they do not have the same level of security as well-known information technology components. So, AI/ML threats and their impacts can be overlooked. On the other hand, due to inherent characteristics of AI/ML components and design of AI/ML pipeline, AI/ML services can be a target for sophisticated attacks. In order to provide a holistic security view, the effect of AI/ML components should be investigated, threats should be identified, and countermeasures should be planned. Therefore, in this study, which is an extended version of our recent study (Karaçay et al. 2023), we shed the light on the use of AI/ML services including generative large language model scenarios in All-Senses meeting use case and their security aspects by carrying out a threat modeling using the STRIDE framework and attack tree methodology. Additionally, we point out some countermeasures for identified threats.