Unmanned aerial vehicles (UAVs) are also increasingly becoming more often in the transportation infrastructure of smart cities, so that they can successfully achieve real-time observation of traffic, emergency coordination, and two-way communication relaying. However, the security and privacy risks arising in open, highly mobile intelligent transportation systems (ITS) enabled by UAVs are critical, as they pose threats of impersonation, replay, Sybil, and tracking attacks. Secondly, standard static authentication mechanisms are unable to support dynamic risk environments and excessive resource consumption on UAV platforms with limited capacity. To address these challenges, this study introduces a Generative-AI-assisted Risk-Adaptive Authentication (GRAA) system that modulates the intensity of the authentication process based on risk levels identified by mobility, contextual awareness, and the environment. The framework contains unlinkable pseudonymous credentials and, unlike the accumulator-based revocation scheme and AI-based trust evaluation, it is impossible to correlate sessions. The coherence with the majority of attacks is demonstrated under the formal analysis model, which is also based on the real-or-random (ROR) session key, alongside the justifications of forward secrecy and unlinkability. The performance analysis shows that GRAA can achieve up to 87.9% reduction in computation cost and 56.7% reduction in communication overhead compared to pairing-and-group signature schemes, while lowering the latency and energy consumption of the UAVs in a congested urban setting. Generally, the suggested architecture provides a scalable, convenient, and privacy-friendly authentication system for next-generation smart transportation systems that use UAVs.
Abdusalomov et al. (Thu,) studied this question.