Search

Unmanned aerial vehicles (UAV) have recently proved their ability to afford reliable and cost-effective solutions for many real-world scenarios. The autonomy, mobility and flexibility nature along with communications interoperability have made UAV able to provide a large variety of services. Awareness of context changes and adaptability to current services requirements are the key to UAVs' deployment success. For this reason, machine learning (ML) has been widely used in overcoming the challenges that UAV faces in mobility, communication and resources management. This paper will mainly focus on the proposed UAV-centric ML solutions and their satisfaction with network requirements taking into consideration UAVs' roles, collaboration, cooperation and network changing contexts. Solutions proposed in air to air, air to ground and ground to air communications as well as UAVs-enabled mobile edge computing are investigated for possible future insights. Future works will indeed highlight the need of UAVs' cooperation in the emergent 5G/6G networks. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) have attracted much attention for civil and military uses because of their high mobility and adaptable deployment capabilities in open spaces. They facilitate agile communications and ubiquitous connectivity. UAVs benefit from dominant line-of-sight communication links but are more susceptible to adversary eavesdropping attacks. Since upper-layer cryptography methods may be insufficient, physical-layer security (PLS) is an attractive alternative. PLS capitalizes on the inherent randomness of wireless channels to improve information confidentiality, particularly in UAV systems. This article provides a comprehensive overview of PLS in the context of UAV systems, examining various communication channels, including ground-to-air (G2A), ground-to-ground (G2G), air-to-ground (A2G), and air-to-air (A2A). First, we give a general review of UAV communications, emphasizing its functions as user equipment, base station (BS), and mobile relay. Following that, we provide an overview of PLS and its forms. The survey organizes the most advanced PLS techniques against passive wireless eavesdropping regarding the channels they are designed to protect. These schemes are further categorized into optimization and secrecy performance analysis. We examine technical aspects within each sub-category and classify core contributions based on approaches and objectives to improve secrecy performance. Moreover, we added summary tables of the identified schemes considering optimization and secrecy performance analysis domains for each category, providing an in-depth understanding of their technical aspects. In addition, we discuss open research issues and identify future research directions to address evolving threats and requirements in UAV communications to improve information confidentiality. [ABSTRACT FROM AUTHOR]