Abstract <p>A study was conducted on machine-learning algorithms used for detecting unauthorized interference in the air-traffic-management communication environment. Decision-tree algorithms, neural networks, support vector machines, Bayesian classification, and K-means clustering were examined. Their features, advantages, and limitations in the context of aviation networks are described. The use of a method for analyzing multidimensional combinations of network-traffic features is proposed to identify indicators of unauthorized interference. The scientific novelty lies in the proposed method, and a comparative analysis with known solutions is presented.</p>