Yazar "Çevik, Nurşah" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Anomaly detection system for ADS-B data: Attack vectors and machine learning models
    (Elsevier B.V., 2025) Çevik, Nurşah; Akleylek, Sedat
    The topic of security challenges and solutions for Automatic Dependent Surveillance-Broadcast (ADS-B) systems is becoming more critical day-to-day because of the increasing air traffic volume. Since aircraft and ground stations receive broadcast ADS-B data cannot check the source and integrity of data, ADS-B systems can be spoofed easily by transmitting false data. In this paper, we develop an anomaly detection system for ADS-B data as a security solution. Various parameter sets were analyzed to identify critical ones. We created attack vectors for eight different attack scenarios, such as spoofing, message injection, and virtual trajectory change attacks, and created hybrid datasets by combining different attack vectors to increase the detection ability of different attack scenarios. These datasets have covered a wide range of attack scenarios to increase the robustness of anomaly detection assessments. We used attack datasets to evaluate the performance of different ML and DL models. The random forest classifier and the extra tree classifier are the standout performers, both achieving an impressive accuracy of 0.999. The decision tree classifier, with an accuracy of 0.992, also demonstrates strong performance, though slightly below that of the random forest and extra tree models. The results of the decision tree classifier have the lowest false negative and false positive rate, which are 0.004 and 0, respectively. Among the deep learning models, the multilayer perceptron model achieves notable success with an accuracy of 0.981744. Based on the results of our model, we increase the accuracy and reliability compared to existing methods. Additionally, we share our datasets to encourage further research and enable other researchers to expand our findings. © 2024 Elsevier B.V.
  • Küçük Resim Yok
    Öğe
    Comparison of machine learning based anomaly detection methods for ADS-B system
    (Springer science and business media deutschland GmbH, 2025) Çevik, Nurşah; Akleylek, Sedat
    This paper introduces an anomaly/intrusion detection system utilizing machine learning techniques for detecting attacks in the Automatic Detection System-Broadcast (ADS-B). Real ADS-B messages between Türkiye's coordinates are collected to train and test machine learning models. After data collection and pre-processing steps, the authors generate the attack datasets by using real ADS-B data to simulate two attack scenarios, which are constant velocity in-crease/decrease and gradually velocity increase or decrease attacks. The efficacy of five machine learning algorithms, including decision trees, extra trees, gaussian naive bayes, k-nearest neighbors, and logistic regression, is evaluated across different attack types. This paper demonstrates that tree-based algorithms consistently exhibit superior performance across a spectrum of attack scenarios. Moreover, the research underscores the significance of anomaly or intrusion detection mechanisms for ADS-B systems, highlights the practical viability of employing tree-based algorithms in air traffic management, and suggests avenues for enhancing safety protocols and mitigating potential risks in the airspace domain.