AI-Driven Smishing Detection in Android Devices Using TinyBERT and Aquila Optimization

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The increasing prevalence of smishing (SMS phishing) attacks on mobile devices poses significant security risks, particularly for Android users. Traditional spam detection techniques often fail to accurately distinguish between legitimate and malicious messages due to the complexity and contextual nature of smishing. In this paper, we propose an AI-driven smishing detection approach using TinyBERT for feature extraction and Aquila Optimization (AO) to optimize a deep learning model. With AO-tuned hyperparameters, the proposed model achieved an accuracy of 96.81%, outperforming standard models like GRU, LSTM, and SVM. Our approach offers a robust, efficient solution for Android smishing detection.

Original languageEnglish
Title of host publication27th International Conference on Advanced Communications Technology
Subtitle of host publicationToward Secure and Comfortable Life in AI Cambrian Explosion Era!!, ICACT 2025 - Proceedings
Pages99-105
Number of pages7
ISBN (Electronic)9791188428137
DOIs
Publication statusPublished - 2025
Event27th International Conference on Advanced Communications Technology, ICACT 2025 - Pyeong Chang, Korea, Republic of
Duration: 16 Feb 202519 Feb 2025

Publication series

NameInternational Conference on Advanced Communication Technology, ICACT
ISSN (Print)1738-9445

Conference

Conference27th International Conference on Advanced Communications Technology, ICACT 2025
Country/TerritoryKorea, Republic of
CityPyeong Chang
Period16/02/2519/02/25

Keywords

  • Android Security
  • Aquila Optimization
  • SMS Phishing
  • Smishing Detection
  • TinyBERT

Fingerprint

Dive into the research topics of 'AI-Driven Smishing Detection in Android Devices Using TinyBERT and Aquila Optimization'. Together they form a unique fingerprint.

Cite this