EUVIMEDEUVIMED entdecken
Crossref

Integration of Cyber Threat Intelligence and machine Learning for Phishing Detection: A Review

Aishabanu Multani, Santosh Saha

International Journal of Innovative Science and Research Technology · 30.05.2026 · 2483

DOI: 10.38124/ijisrt/26may787 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 30.05.2026. Verfasst von Aishabanu Multani und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The dynamic change in the nature of various cyber threats, especially the threat of phishing, has identified the limitations of traditional security solutions such as rule-based systems, signature-based systems, etc. Cyber Threat Intelligence has emerged as an effective security practice that provides contextual information on threat actors, techniques, etc., whereas Machine Learning has also emerged as an effective security practice that offers solutions to automated threat detection using data analysis patterns. Although both of these security practices have immense potential, the integration of both has not yet been explored, as seen in the existing literature on the integration of both security practices to offer effective security solutions, especially against the threat of phishing. This paper has been designed to offer an extensive review of the existing literature on the integration of Cyber Threat Intelligence, Machine Learning, and security solutions, especially against the threat of phishing, as seen in the literature from 2016 to 2025.On the other hand, the comparative analysis of the challenges identifies the need to address the issue of unstructured sources of intelligence, the problem of limited interoperability, the issue of scalability, the problem of lack of explainability, and the problem of insufficient validation of the solutions in the real world. Moreover, the current models of phishing detection, despite their high benchmark accuracy, have limitations related to their adaptability, multilinguality, and adversarial robustness. With the identified research gaps, this review highlights the importance of developing semantically enriched CTI solutions, knowledge graph-based solutions, Large Language Model-based solutions, and adaptive learning-based solutions to facilitate the development of explainable and real-time solutions to the problem of cybersecurity.

Zitieren

APA

Multani, A., & Saha, S. (2026). Integration of Cyber Threat Intelligence and machine Learning for Phishing Detection: A Review. International Journal of Innovative Science and Research Technology, 2483. https://doi.org/10.38124/ijisrt/26may787

Vancouver

Multani A, Saha S. Integration of Cyber Threat Intelligence and machine Learning for Phishing Detection: A Review. International Journal of Innovative Science and Research Technology. 2026:2483. doi:10.38124/ijisrt/26may787

BibTeX
@article{Multani2026,
  author = {Multani, Aishabanu and Saha, Santosh},
  title = {Integration of Cyber Threat Intelligence and machine Learning for Phishing Detection: A Review},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {2483},
  doi = {10.38124/ijisrt/26may787}
}
Kostenlos starten →