Phishing remains a persistent and evolving cyber threat, constantly adapting its tactics to bypass traditional security measures. The advent of Machine Learning (ML) and Neural Networks (NN) has significantly enhanced the capabilities of automated phishing detection systems. This comprehensive review systematically examines the landscape of ML- and NN-based approaches for identifying and mitigating phishing attacks. Our analysis, based on a rigorous search methodology, focuses on articles published between 2017 and 2024 across relevant subject areas in computer science and mathematics. We categorize existing research by phishing delivery channels, including websites, electronic mail, social networking, and malware. Furthermore, we delve into the specific machine learning models and techniques employed, such as various algorithms, classification and ensemble methods, neural network architectures (including deep learning), and feature engineering strategies. This review provides insights into the prevailing research trends, identifies key challenges, and highlights promising future directions in the application of machine learning and neural networks for robust phishing detection.
30 September 2025 in Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
Phishing poses a significant risk in the field of digital security, requiring effective methods for identifying fraudulent websites. This study evaluated the performance of nine machine learning classification models in the context of phishing website detection. Two different input datasets were prepared: the first included the full HTML code, while the second was based on a set of features extracted from that code. The analysis revealed that models trained on the extracted features achieved nearly twice the detection performance compared to those operating on raw HTML code. The use of majority voting further improved classification effectiveness. The study results confirm that proper feature selection and the integration of outputs from multiple models significantly enhance the effectiveness of systems for detecting online threats.
The goal is to model the behaviour of an apodized fibre Bragg grating (FBG) under impulsive strain of rectangular shape. The transfer matrix method has been applied in this analysis. The changes induced in a spectrum of FBG are calculated based on the piecewise-uniform period assumption for chirped gratings. The result demonstrates changing spectrum of a FBG during processing impulsive quantities with different amplitudes.
The article presents the influence of the length of fiber Bragg grating with linear changeable period on processing accuracy of impulsive excitations acting along the longitudinal fiber axis. Using transfer matrix method the power reflectivity spectrums caused by impulsive strains are obtained. On this basis, assuming that grating's output signal is of centroidal frequency, the mean square error was evaluated as a function of the ratio of the length of the grating to the length of impulse, for different shapes of impulsive strains.
This paper presents theoretical analysis of impulsive strain processing by fiber Bragg Grating (FBG) with linearly changeable period. Tensile and compression excitations acting along the longitudinal fiber axis are studied. The prepared calculation is based on the piecewise-uniform period assumption for chirped grating. Then the obtained reflected spectrum is analyzed by calculating its centroid frequency. This allows it to calculate rise time error as a function of length of distortion leading edge and grating length which allows it to establish influence of grating length on processing accuracy.