Maqola

A Machine Learning-Based Framework for Malicious URL Detection in Cybersecurity

Tanjim MahmudRangamati Science and Technology University,Dept. of CSE,Rangamati,Bangladesh,4500G.M. Sakhawat HossainRangamati Science and Technology University,Dept. of Computer Science and Engineering,Rangamati,Bangladesh,4500Md. Hasan AliRangamati Science and Technology University,Dept. of CSE,Rangamati,Bangladesh,4500Tanvir HasanRangamati Science and Technology University,Dept. of CSE,Rangamati,Bangladesh,4500Md. Faisal Bin Abdul AzizComilla University,Dept. of Computer Science and Engineering,Comilla,BangladeshMohammad Tarek AzizUniversity of Engineering and Technology,Dept. of CSE Chittagong,Chittagong,BangladeshMohammad Shahadat HossainUniversity of Chittagong,Dept. of Computer Science and Engineering,Chittagong,Bangladesh,4331Karl AnderssonLuleå University of Technology,Cybersecurity Laboratory,Luleå,Sweden,97187

2025en

ABI

Annotatsiya

Malicious URLs represent a significant cybersecurity threat, facilitating malware distribution and data theft. This paper explores a ML-based framework for malicious URL detection, providing a comparative analysis of DL and traditional ML approaches. Eight ML models─LR, SVM, DT, KNN, GNB, RF, XGBoost, and LightGBM─are benchmarked against three DL models: LSTM, BiLSTM, and GRU. The results reveal that traditional ML models, particularly RF, XGBoost, and LightGBM, achieve superior performance with accuracy scores of up to 92%, outperforming DL models, which achieve accuracy rates of 90%, 91%, and 88%, respectively. To further enhance detection performance, a stacking model combining these techniques is proposed, achieving a remarkable accuracy of 99.99%. This research underscores the potential of stacked models to significantly improve malicious URL detection, offering advanced solutions to strengthen cybersecurity frameworks for both individuals and organizations.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1109/icict64582.2025.00016

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar