What question did this study set out to answer?

The aim is to develop a deep learning model that accurately detects malicious URLs by utilizing structural and contextual features.

A study on malicious URL detection based on BiGruCNN-MHA-FTW

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates a deep learning approach for effectively detecting malicious URLs, indicating significant advancements for cybersecurity.

The aim is to develop a deep learning model that accurately detects malicious URLs by utilizing structural and contextual features.
Developed the BMFTW model integrating BiGRU, CNN, and multi-head attention.
Utilized character-level index mapping and Word2Vec embeddings for feature representation.
Implemented hybrid FTW loss to handle class imbalance and enhance performance.
Applied L2 regularization, dropout, and learning rate decay to improve generalization.
Conducted experiments on the Malicious and Benign URLs dataset.
Achieved 98.28% accuracy in detecting malicious URLs.
Reached 94.25% precision and 98.71% recall in binary classification.
Attained a 96.43% F1-score in binary detection and 94.93% F1-score in multi-class detection.
Outperformed baseline models with significant statistical confidence.

Lv et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates a deep learning approach for effectively detecting malicious URLs, indicating significant advancements for cybersecurity.

The aim is to develop a deep learning model that accurately detects malicious URLs by utilizing structural and contextual features.
Developed the BMFTW model integrating BiGRU, CNN, and multi-head attention.
Utilized character-level index mapping and Word2Vec embeddings for feature representation.
Implemented hybrid FTW loss to handle class imbalance and enhance performance.
Applied L2 regularization, dropout, and learning rate decay to improve generalization.
Conducted experiments on the Malicious and Benign URLs dataset.
Achieved 98.28% accuracy in detecting malicious URLs.
Reached 94.25% precision and 98.71% recall in binary classification.
Attained a 96.43% F1-score in binary detection and 94.93% F1-score in multi-class detection.
Outperformed baseline models with significant statistical confidence.

Lv et al. (2026) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark