Can Open and AI-Enabled 6G RAN Be Secured?
Sanaz Soltani, Mohammad Shojafar, Rahim Taheri, Rahim Tafazolli
Abstract
The forthcoming 6g network goes beyond a new and Open Radio Access Network (O-RAN), allowing increased flexibility and interoperability. Intelligent radio network orchestration will be integral in the 6G era in order to control the radio network for near-real-time and nonreal-time applications. O-RAN reaches the goal of network flexibility through AI-enabled functions, particularly with machine learning (ML) systems. Hence, the role of AI/ML is immense in the envisioned 6G paradigm. However, the alliance between O-RAN and AI/ML may also be a double-edged sword in 6G as their applicability for protecting or infringing security and privacy. Hyperconnected Internet of Everything data collection for 6G application services raises privacy concerns. Data privacy, location privacy, and identity privacy will all be compromised as a result of data theft involving resource-constrained IoT devices. In addition, the O-RAN architecture consists almost entirely of virtualization and software functionality, which expands the threat and attack surface of the network. The open and AI-enabled 6G radio network is therefore susceptible to hacking, attacks, and disruptions.