cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fauji Nurdin ST. Mudo
Contact Email
kangdensus88@gmail.com
Phone
+6285246960680
Journal Mail Official
mambang@unism.ac.id
Editorial Address
Jl. Pramuka No.02 Kelurahan Pemurus Luar Kecamatan Banjarmasin Timur Kota Banjarmasin Kalimantan Selatan
Location
Kota banjarmasin,
Kalimantan selatan
INDONESIA
INSTALL: Information System and Technology Journal
Published by Universitas Sari Mulia
ISSN : -     EISSN : 30481597     DOI : https://doi.org/ 10.33859/install
Core Subject : Science, Education,
Computer Science & IT Decision Sciences, Operations Research & Management Education
The Focus and Scope of this Journal is related to : Information system Information Technology Business commerce Management technology Business Technology
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 41 Documents
 1   2   3   4   5 
The Effectiveness of early stopping on the efficiency of training CNN models for phishing URL identification Rifani, Muhammad Rifani; Prastya, Septyan Eka; Zulfadhilah, Muhammad; Munsyi
INSTALL: Information System and Technology Journal Vol 3 No 1 (2026): INSTALL : Information System and Technology Journal
Publisher : LPPM Universitas Sari Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33859/install.v3i1.1024

Abstract

Phishing is a significant cybersecurity threat in which malicious URLs deceive users to steal sensitive data. Traditional detection methods, such as blacklists, often fail to keep pace with evolving phishing techniques. Deep learning, particularly Convolutional Neural Networks (CNNs), offers strong potential in phishing URL classification by capturing structural and semantic character-level patterns. However, CNN training demands high computational resources and risks overfitting. This study investigates the effectiveness of early stopping as a regularization technique to improve efficiency and generalization in character-based CNN models. Using a large-scale dataset of 130.080 URLs across four classes (benign, phishing, malware, defacement), the model employed character tokenization, embedding, convolution-pooling layers, and softmax classification. Early stopping monitored validation loss with patience values of 3, 5, and 10 epochs. Results show a 51% training time reduction and accuracy improvement from 96% to 97%, confirming early stopping as an efficient and robust detection approach.

Page 5 of 5 | Total Record : 41

 1   2   3   4   5 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol 3 No 1 (2026): INSTALL : Information System and Technology Journal Vol 2 No 3 (2025): INSTALL : Information System and Technology Journal Vol 2 No 2 (2025): INSTALL : Information System and Technology Journal Vol 2 No 1 (2025): INSTALL : Information System and Technology Journal Vol 1 No 3 (2024): INSTALL : Information System and Technology Journal Vol 1 No 2 (2024): INSTALL : Information System and Technology Journal Vol 1 No 1 (2024): INSTALL : Information System and Technology Journal