Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 12, 2026Journal of Cybersecurity and PrivacyOpen Access

NetGuard: A Hybrid Framework for Intelligent and Scalable Malicious URL Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

SKSaja Dheyaa KhudhurUniversity of Technology - IraqSSSama S. SamaanUniversity of Technology - IraqOTOmar N. M. TaherUniversity of Technology - Iraq

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates efficient malicious URL detection using hybrid PDS and machine learning, suggesting robust internet security solutions.

Key Points

  • The aim is to develop an intelligent and scalable framework for detecting malicious URLs amidst increasing online threats.
  • Proposed the hybrid framework NetGuard integrating probabilistic data structures with machine learning.
  • Utilized counting Bloom filters and scalable Bloom filters for efficient URL detection and management.
  • Trained Decision Trees and Random Forest classifiers on the SupURLsIdDs dataset comprising diverse URL features.
  • HSDF maintained a controlled false-positive rate of approximately 0.01 and a latency of 10−5 s for queries.
  • Memory consumption for 222,000 URLs was approximately 2.7 MB, a 99.88% improvement over the Random Forest model's 2253.17 MB.
  • Random Forest achieved an overall classification accuracy of approximately 96% on large-scale URL data.

Cite This Study

Khudhur et al. (2026) studied this question.

synapsesocial.com/papers/6a2ba4a18101cf8926f02fbehttps://doi.org/10.3390/jcp6030102
View Full Paper
Ask AI
Bookmark
Share