Improving Phishing Website Detection Using a Hybrid Two-level Framework for Feature Selection and XGBoost Tuning

Abstract

In the last few decades, the World Wide Web has become a necessity that offers numerous services to end users. The number of online transactions increases daily, as well as that of malicious actors. Machine learning plays a vital role in the majority of modern solutions. To further improve Web security, this paper proposes a hybrid approach based on the eXtreme Gradient Boosting (XGBoost) machine learning model optimized by an improved version of the well-known metaheuristics algorithm. In this research, the improved firefly algorithm is employed in the two-tier framework, which was also developed as part of the research, to perform both the feature selection and adjustment of the XGBoost hyper-parameters. The performance of the introduced hybrid model is evaluated against three instances of well-known publicly available phishing website datasets. The performance of novel introduced algorithms is additionally compared against cutting-edge metaheuristics that are utilized in the same framework. The first two datasets were provided by Mendeley Data, while the third was acquired from the University of California, Irvine machine learning repository. Additionally, the best performing models have been subjected to SHapley Additive exPlanations (SHAP) analysis to determine the impact of each feature on model decisions. The obtained results suggest that the proposed hybrid solution achieves a superior performance level in comparison to other approaches, and that it represents a perspective solution in the domain of web security.

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

“…These algorithms, and algorithms derived from their base have been applied in several fields with promising outcomes. Some noteworthy examples of metaheuristics applied to optimization problems include examples for crude oil price forecasting ( Jovanovic et al, 2022 ; Al-Qaness et al, 2022 ), Ethereum and Bitcoin prices predictions ( Stankovic et al, 2022b ; Milicevic et al, 2023 ; Petrovic et al, 2023 ; Gupta & Nalavade, 2022 ), industry 4.0 ( Jovanovic et al, 2023b ; Dobrojevic et al, 2023 ; Para, Del Ser & Nebro, 2022 ), medicine ( Zivkovic et al, 2022a ; Bezdan et al, 2022 ; Budimirovic et al, 2022 ; Stankovic et al, 2022a ), security ( Zivkovic et al, 2022b ; Savanović et al, 2023 ; Jovanovic et al, 2023c ; Zivkovic et al, 2022c ), cloud computing ( Thakur & Goraya, 2022 ; Mirmohseni, Tang & Javadpour, 2022 ; Bacanin et al, 2022d ; Zivkovic et al, 2021 ), and environmental sciences ( Jovanovic et al, 2023d ; Bacanin et al, 2022b ; Kiani et al, 2022 ).…”

Computer-Vision Unmanned Aerial Vehicle Detection System Using YOLOv8 Architectures

“…Moreover, hybrid methods between machine/deep learning and metaheuristics excel in other application domains as well, as evidenced by numerous successful recent applications including medicine [22,13,8,27,32,6,24], agriculture [25], environmental monitoring [5,20], economy [13,41,38] and power grids [29,14,3,39,45]. Other notable applications include weather forecasting [21], cloud computing [7,33,4,9], wireless sensor networks [46,11,44] and intrusion detection [35,36,23,15]. Also, it is worth mentioning that there are also many applications of enhanced metaheuristics methods [40,42].…”

Performance evaluation of metaheuristics-tuned recurrent neural networks for electroencephalography anomaly detection

“…Metaheuristic algorithms have many uses in a variety of sectors due to their high performance when taking up general optimizations. Some fascinating examples include credit card fraud detection ( Jovanovic et al, 2022a ; Petrovic et al, 2022 ), security and intrusion detection ( Jovanovic et al, 2023c ; Jovanovic et al, 2022b ; Bacanin et al, 2022 ), cloud-edge computing ( Bacanin et al, 2019 ; Bezdan et al, 2020 ; Zivkovic et al, 2021b ), tackling challenging obstacles in emerging industries ( Jovanovic et al, 2023a ), forecasting COVID-19 cases ( Zivkovic et al, 2021c ; Zivkovic et al, 2021a ), as well as in healthcare ( Bezdan et al, 2021 ; Zivkovic et al, 2022a ; Zivkovic et al, 2022c ; Jovanovic et al, 2023b ; Jovanovic et al, 2022d ; Tair et al, 2022 ). Moreover, metaheuristics have demonstrated remarkable effectiveness in optimizing time series forecasting ( Jovanovic et al, 2022c ; Stankovic et al, 2022 ; Bacanin et al, 2023 ).…”