Practical Adversarial Attacks Against AI-Driven Power Allocation in a Distributed MIMO Network

Abstract--In distributed multiple-input multiple-output (D-allocate their power among users to optimize the system's To overcome the complexity problem, Bashar et al. [3] In this study, we investigate the potential effects of adversarial attacks targeting AI-driven power control systems in I. We explain the main constraints of the adversary Deep learning is expected to be an important enabler for resulting from the distributed nature of wireless domain and many wireless communication challenges in 6G. Deep neural focus only on the possible practical scenarios to observe the networks (DNNs) are being proposed to handle a wide range severity of adversarial attack threats. We work on attacks based of wireless communication tasks including encoding/decoding on universal adversarial perturbation (UAP) which are not operations, spectrum sensing and RF signal classification. We propose a novel modified UAP (m-D-MIMO is a new network type considered for 6G communication UAP) technique that crafts a specific perturbation for each systems where many radio units (RUs) are geographically input where there is only a partial knowledge about some of distributed in a region to increase the coverage input entries.