Trusting the accuracy of data inputted on online platforms can be difficult
due to the possibility of malicious websites gathering information for unlawful
reasons. Analyzing each website individually becomes challenging with the
presence of such malicious sites, making it hard to efficiently list all
Uniform Resource Locators (URLs) on a blacklist. This ongoing challenge
emphasizes the crucial need for strong security measures to safeguard against
potential threats and unauthorized data collection. To detect the risk posed by
malicious websites, it is proposed to utilize Machine Learning (ML)-based
techniques. To this, we used several ML techniques such as Hist Gradient
Boosting Classifier (HGBC), K-Nearest Neighbor (KNN), Logistic Regression (LR),
Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), Light
Gradient Boosting Machine (LGBM), and Support Vector Machine (SVM) for
detection of the benign and malicious website dataset. The dataset used
contains 1781 records of malicious and benign website data with 13 features.
First, we investigated missing value imputation on the dataset. Then, we
normalized this data by scaling to a range of zero and one. Next, we utilized
the Synthetic Minority Oversampling Technique (SMOTE) to balance the training
data since the data set was unbalanced. After that, we applied ML algorithms to
the balanced training set. Meanwhile, all algorithms were optimized based on
grid search. Finally, the models were evaluated based on accuracy, precision,
recall, F1 score, and the Area Under the Curve (AUC) metrics. The results
demonstrated that the HGBC classifier has the best performance in terms of the
mentioned metrics compared to the other classifiers.

为了检测恶意网站的风险，我们提出利用基于机器学习的技术，通过对数据输入、恶意网站、机器学习技术和网站检测等关键词进行分析，并优化算法，最终通过多种指标对模型进行评估，实验结果表明 Hist Gradient Boosting Classifier (HGBC) 在各项指标上表现最好。

基于网格搜索方法的优化 Hist Gradient Boosting 分类器的恶意 URL 检测

Malicious URL Detection using optimized Hist Gradient Boosting  Classifier based on grid search method

The detection of malicious websites has become a critical issue in
cybersecurity. Therefore, this paper offers a comprehensive review of
data-driven methods for detecting malicious websites. Traditional approaches
and their limitations are discussed, followed by an overview of data-driven
approaches. The paper establishes the data-feature-model-extension pipeline and
the latest research developments of data-driven approaches, including data
preprocessing, feature extraction, model construction and technology extension.
Specifically, this paper compares methods using deep learning models proposed
in recent years. Furthermore, the paper follows the
data-feature-model-extension pipeline to discuss the challenges together with
some future directions of data-driven methods in malicious website detection.

本文系统评述了针对恶意网站的数据驱动方法，包括数据预处理、特征提取、模型构建和技术拓展，并对近年来提出的基于深度学习模型的方法进行了比较。最后，讨论了数据驱动方法面临的挑战和未来发展方向。