Scholarlink

<p>Phishing is a very serious form of security threat to the online world. The traditional detection techniques are not able to match the constantly changing strategies of the attackers. The study proposes an advanced phishing detection model on the basis of Capsule Networks (CapsNet) and with the integration of XGBoost and LSTM as the feature extraction models, and Gradient Boosting as the features selection model. The system utilizes email information and therefore gets important characteristics like the sender details, email subject lines, email body, and email URLs. This data is thereby preprocessing the model with binary coding. To evaluate the model, various performance metrics are calculated, including Accuracy, Precision, Recall and F1-score. The CapsNet model classifies with an accuracy of 99.62%, precision of 99.53%, a recall of 99.70% and an F1-score of 99.62%. It has outperformed other current phishing detection methods like PDMLP, AdaBoost and Naive Bayes (NB), especially in sensitivity and overall classification performance. Additionally, the low FPR (0.0173) and FNR (0.022889) of the model further increase its reliability for real-world phishing detection. The proposed hybrid system looks very promising in the fight against advanced phishing attacks as it can detect phishing websites and emails remarkably well.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced phishing detection using binary encoding XGBoost and LSTM feature extraction and capsule network classification

  • 期刊论文

  • 发表日期：

    2026年1月6日

查看全文
  • Azath Mubarakali

摘要

Phishing is a very serious form of security threat to the online world. The traditional detection techniques are not able to match the constantly changing strategies of the attackers. The study proposes an advanced phishing detection model on the basis of Capsule Networks (CapsNet) and with the integration of XGBoost and LSTM as the feature extraction models, and Gradient Boosting as the features selection model. The system utilizes email information and therefore gets important characteristics like the sender details, email subject lines, email body, and email URLs. This data is thereby preprocessing the model with binary coding. To evaluate the model, various performance metrics are calculated, including Accuracy, Precision, Recall and F1-score. The CapsNet model classifies with an accuracy of 99.62%, precision of 99.53%, a recall of 99.70% and an F1-score of 99.62%. It has outperformed other current phishing detection methods like PDMLP, AdaBoost and Naive Bayes (NB), especially in sensitivity and overall classification performance. Additionally, the low FPR (0.0173) and FNR (0.022889) of the model further increase its reliability for real-world phishing detection. The proposed hybrid system looks very promising in the fight against advanced phishing attacks as it can detect phishing websites and emails remarkably well.