EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An AI-Driven Framework for Cyber-Audit Through Encrypted Traffic Analysis of Instant Messaging and Smartphone Applications

Kheddari Tedjani

Journal of Intelligent Decision Making and Information Science · 09.09.2026 · 3 (18s) · 662-693

DOI: 10.17762/jidmis.v3.5751 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 09.09.2026. Verfasst von Kheddari Tedjani. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread adoption of encrypted instant messaging and smartphone applications presents significant challenges for cyber-audit and network traffic analysis, as encryption restricts conventional content-based inspection of communication payloads. This paper proposes an AI-driven framework for cyber-audit through encrypted traffic analysis of instant messaging and smartphone applications. The framework integrates six machine learning classifiers—Logistic Regression, Decision Tree, Random Forest, Gaussian Naive Bayes, Support Vector Machine, and Stochastic Gradient Descent—to identify and classify communication activities based on observable network traffic characteristics without accessing encrypted message contents. Recursive Feature Elimination (RFE) is incorporated to select the most informative traffic features, reduce dimensionality, and improve computational efficiency. The proposed methodology analyzes encrypted traffic generated during text messaging, media transmission, voice and video communication, using statistical, temporal, and behavioral traffic patterns. Experimental evaluation examines classification performance using Accuracy, Precision, Recall, F1-score, and AUC, alongside the impact of feature selection on analytical efficiency. The findings demonstrate the potential of combining machine learning and RFE to support the identification and characterization of encrypted communication activities without payload decryption. The proposed framework provides a non-payload-based analytical approach for supporting cyber-audit and network investigation while preserving the confidentiality of message content.

Zitieren

APA

Tedjani, K. (2026). An AI-Driven Framework for Cyber-Audit Through Encrypted Traffic Analysis of Instant Messaging and Smartphone Applications. Journal of Intelligent Decision Making and Information Science, 3(18s), 662-693. https://doi.org/10.17762/jidmis.v3.5751

Vancouver

Tedjani K. An AI-Driven Framework for Cyber-Audit Through Encrypted Traffic Analysis of Instant Messaging and Smartphone Applications. Journal of Intelligent Decision Making and Information Science. 2026;3(18s):662-693. doi:10.17762/jidmis.v3.5751

BibTeX
@article{Tedjani2026,
  author = {Tedjani, Kheddari},
  title = {An AI-Driven Framework for Cyber-Audit Through Encrypted Traffic Analysis of Instant Messaging and Smartphone Applications},
  journal = {Journal of Intelligent Decision Making and Information Science},
  year = {2026},
  volume = {3},
  number = {18s},
  pages = {662--693},
  doi = {10.17762/jidmis.v3.5751}
}
Kostenlos starten →