What does this research mean for the field?

A layer-wise fusion model combining local convolution and global attention (PLG-URLNet) achieves 98.59% accuracy in detecting malicious URLs and effectively identifies obfuscated variants even under stringent temporal generalization scenarios. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to develop a new method for detecting malicious URLs by combining local and global feature extraction.

June 7, 2026ElectronicsOpen Access

PLG-URLNet: Layer-Wise Fusion of Local Convolution and Global Attention for Detecting Malicious URLs

View Full Paper

Ask AI

Bookmark

Authors

YXYongcai XiaoState Grid Corporation of China (China)YLY LiuIONICS Mass Spectrometry (Canada)YHYueshun HeEast China University of Technology

Discussion

Member takes

Implication

Randomized trial demonstrates improved detection of malicious URLs in complex networks, suggesting enhanced security measures.

Key Points

This research aims to develop a new method for detecting malicious URLs by combining local and global feature extraction.
Developed PLG-URLNet, a two-branch detection model with convolutional and transformer branches.
Implemented a hierarchical interaction module in each layer for effective feature integration.
Adopted both standard evaluation and time-sequential partitioning to validate model performance.
Achieved an accuracy of 98.59% in detecting malicious URLs.
Demonstrated superior performance in identifying obfuscated and variant URLs during temporal generalization.
Effectively integrated local and global patterns to enhance model representation capabilities.

Cite This Study

Xiao et al. (2026) studied this question.

synapsesocial.com/papers/6a250b4c7def13d035e1b4ba https://doi.org/10.3390/electronics15112485

View Full Paper

Ask AI

Bookmark

PLG-URLNet: Layer-Wise Fusion of Local Convolution and Global Attention for Detecting Malicious URLs

Discussion

Member takes

Implication

Key Points

Cite This Study

PLG-URLNet: Layer-Wise Fusion of Local Convolution and Global Attention for Detecting Malicious URLs

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider