Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 6, 2025Scientific ReportsOpen Access

Lightweight malicious URL detection using deep learning and large language models

View Full Paper
Ask AI
Bookmark
Share

Authors

HKHareem KibriyaAir UniversityRARashid AminUniversity of Engineering and Technology TaxilaSASultan S. AlshamraniTaif University

Discussion

Loading...

Member takes

Implication

This analysis improves malicious URL detection in cybersecurity, demonstrating a deep learning approach to address evolving attack patterns.

Key Points

  • Achieving 97.5% accuracy, the model effectively categorizes malicious and benign URLs, enhancing user protection.
  • With the help of large language models, the system generates high-quality URL embeddings for better detection accuracy.
  • Utilizing LSTM and GRU layers, the model captures long-range dependencies, making it robust against emerging threats.
  • The integration of eXplainable AI techniques ensures model transparency, fostering trust in real-time cybersecurity applications.

Cite This Study

Kibriya et al. (2025) studied this question.

synapsesocial.com/papers/69337cefb3f947a0a125a3a7https://doi.org/10.1038/s41598-025-26653-2
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1From Hyper-dimensional Structures to Linear Structures: Maintaining Deduplicated Data’s Locality2022 · 110 citations
  2. 2Malicious URL Detection and Classification Analysis using Machine Learning Models2023 · 44 citations
  3. 3PhishStorm: Detecting Phishing With Streaming Analytics2014 · 265 citations