HOTD

Proposed a Holistic Cross-Layer Time Delay Attack Detection Framework (HOTD) for UAV networks, designed to effectively identify time delay attacks that are both challenging to detect and straightforward to implement. The framework begins with a comprehensive selection of delay-related features across each layer of UAV networks. Using supervised learning, a consistency model is constructed to map the relationship between these features and their corresponding forwarding delays. Based on this model, the consistency degree of each node is calculated. Finally, the K-Means clustering algorithm is employed to classify nodes as either malicious or benign based on their consistency degrees. (2021–2022, published in the Journal of Parallel and Distributed Computing (JPDC) [CORE A, CCF B, SCI-Q1])