Monday, November 16, 2026
Science
No Result
View All Result
  • Login
  • HOME
  • SCIENCE NEWS
  • CONTACT US
  • HOME
  • SCIENCE NEWS
  • CONTACT US
No Result
View All Result
Scienmag
No Result
View All Result
Home Science News

Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability

November 9, 2026
in Science News
Blake Davidson
By Blake Davidson Scienmag Editorial Profile - Data Science
Reading Time: 2 mins read
0
Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability

Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability

65
SHARES
587
VIEWS
Share on FacebookShare on Twitter
ADVERTISEMENT

A deep learning mechanism designated as CSqL-m-H2LA-GRBiTM has been developed to provide robust smishing detection by capturing both spatial and temporal features in mobile messaging, according to a study published in Scientific Reports. Authored by Mohd Shoaib, the research introduces an artificial intelligence architecture designed to identify SMS phishing attempts as network adversaries continue to evolve. By processing complex communication patterns through integrated attention and recurrent units, the proposed system demonstrates high efficiency compared with traditional smishing detection methods.

Smishing detection represents an effective and essential research domain that has grown increasingly critical over the past decade. Conventional research in this area attempted to achieve accurate smishing detection but encountered several persistent challenges. Among the primary obstacles identified in earlier studies were a shortage of large datasets, the improper classification of legitimate and malicious messages, high computational resource utilization, and high false positive rates.

To overcome these limitations, the proposed CSqL-m-H2LA-GRBiTM model combines a Gated Recurrent Unit with Bidirectional Long Short-Term Memory to capture information concerning both spatial and temporal features. This structural configuration elevates the model’s efficiency in handling the complex textual and sequential patterns characteristic of smishing attacks.

The architecture incorporates two critical components: a multi-head Hierarchical Location Attention mechanism, designated as m-H2LA, and a Categorical Square Loss function, termed CSqL. The m-H2LA mechanism specifically focuses on relevant messages and their constituent features, boosting the interpretability of the detection framework. Concurrently, the deployment of the CSqL loss function enables robust detection by balancing maximum separation with probabilistic calibration.

In performance evaluations, the CSqL-m-H2LA-GRBiTM framework was tested across two distinct benchmark collections using a 10-fold cross-validation setup (K-fold-10). When evaluated on the SMS phishing dataset, the model achieved an accuracy of 98.36 percent, an F1-score of 96.84 percent, and a log-loss of 5.09.

Subject of Research: Deep learning mechanism for smishing detection

Article Title: CSqL-m-H2LA-GRBiTM: categorical square loss-based multi-head hierarchical location attention enabled deep learning mechanism for smishing detection

Article References: Shoaib, M. (2026). CSqL-m-H2LA-GRBiTM: categorical square loss-based multi-head hierarchical location attention enabled deep learning mechanism for smishing detection. Scientific Reports. https://doi.org/10.1038/s41598-026-77954-z

Image Credits: AI Generated

DOI: 10.1038/s41598-026-77954-z

Keywords: smishing detection, SMS phishing, deep learning, hierarchical attention, gated recurrent unit, bidirectional LSTM, cybersecurity, artificial intelligence, CSqL-m-H2LA-GRBiTM, categorical, square, loss-based

Cite Scienmag News

Blake Davidson. (November 9, 2026). Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability. Scienmag. https://scienmag.com/novel-deep-learning-architecture-improves-sms-phishing-detection-accuracy-and-interpretability/

Blake Davidson. "Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability." Scienmag, 9 November 2026, https://scienmag.com/novel-deep-learning-architecture-improves-sms-phishing-detection-accuracy-and-interpretability/. Accessed 16 November 2026.

Blake Davidson. "Novel Deep Learning Architecture Improves SMS Phishing Detection Accuracy and Interpretability." Scienmag. November 9, 2026. https://scienmag.com/novel-deep-learning-architecture-improves-sms-phishing-detection-accuracy-and-interpretability/

Tags: Artificial Intelligencebidirectional LSTMcategoricalCSqL-m-H2LA-GRBiTMcybersecuritydeep learninggated recurrent unithierarchical attentionloss-basedsmishing detectionSMS phishingsquare
Share26Tweet16
Previous Post

Dual Top Trading Cycles Solves Contractual Consistency in Digital Asset Swaps

Next Post

Machine Learning Reveals Complex Urban Form and Ecosystem Interactions Across Shanghai

Related Posts

Closed-Loop Evolutionary Algorithm Improves Convergence and Diversity in Multi-Objective Optimization
Technology and Engineering

Closed-Loop Evolutionary Algorithm Improves Convergence and Diversity in Multi-Objective Optimization

November 16, 2026
Sustained Higher Body Mass Index Linked to Elevated Uterine Fibroid Risk
Medicine

Sustained Higher Body Mass Index Linked to Elevated Uterine Fibroid Risk

November 16, 2026
Adaptive Cognitive Honeynet Improves Cybersecurity Deception Across Industrial Internet of Things Networks
Technology and Engineering

Adaptive Cognitive Honeynet Improves Cybersecurity Deception Across Industrial Internet of Things Networks

November 16, 2026
FFLE-Net Improves Small Object Detection in Remote Sensing Across Aerial Datasets
Technology and Engineering

FFLE-Net Improves Small Object Detection in Remote Sensing Across Aerial Datasets

November 16, 2026
Adaptive Sharding Mechanism Boosts Blockchain Transaction Throughput for Mobile Edge Computing
Technology and Engineering

Adaptive Sharding Mechanism Boosts Blockchain Transaction Throughput for Mobile Edge Computing

November 16, 2026
MaRENet Outperforms Baselines in Transaction-Level Credit Card Fraud Detection
Technology and Engineering

MaRENet Outperforms Baselines in Transaction-Level Credit Card Fraud Detection

November 16, 2026
Next Post
Machine Learning Reveals Complex Urban Form and Ecosystem Interactions Across Shanghai

Machine Learning Reveals Complex Urban Form and Ecosystem Interactions Across Shanghai

  • Mothers who receive childcare support from maternal grandparents show more optimized

    Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    27656 shares
    Share 11059 Tweet 6912
  • University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept

    1061 shares
    Share 424 Tweet 265
  • Bee body mass, pathogens and local climate influence heat tolerance

    682 shares
    Share 273 Tweet 171
  • Researchers record first-ever images and data of a shark experiencing a boat strike

    546 shares
    Share 218 Tweet 137
  • Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function

    531 shares
    Share 212 Tweet 133
Science

Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!

RECENT NEWS

  • Closed-Loop Evolutionary Algorithm Improves Convergence and Diversity in Multi-Objective Optimization
  • Sustained Higher Body Mass Index Linked to Elevated Uterine Fibroid Risk
  • Adaptive Cognitive Honeynet Improves Cybersecurity Deception Across Industrial Internet of Things Networks
  • FFLE-Net Improves Small Object Detection in Remote Sensing Across Aerial Datasets

Categories

  • Agriculture
  • Anthropology
  • Archaeology
  • Athmospheric
  • Biology
  • Biotechnology
  • Blog
  • Bussines
  • Cancer
  • Chemistry
  • Climate
  • Earth Science
  • Editorial Policy
  • Marine
  • Mathematics
  • Medicine
  • Pediatry
  • Policy
  • Psychology & Psychiatry
  • Science Education
  • Science News
  • Social Science
  • Space
  • Technology and Engineering

Subscribe to Blog via Email

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 5,150 other subscribers

© 2026 Scienmag - Science Magazine

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • HOME
  • SCIENCE NEWS
  • CONTACT US

© 2026 Scienmag - Science Magazine

Discover more from Science

Subscribe now to keep reading and get access to the full archive.

Continue reading