Analyzing Applicability of Phishing Analysis and Prevention Techniques

Author

Khushi Kumari, Mr. Nilesh Khare, Kritika Yadav

Abstract

 Phishing protection must operate across heterogeneous attack channels, changing adversarial tactics, and stringent deployment constraints. Although recent studies report substantial gains from machine learning, deep learning, transformer-based language models, and ensemble classifiers, predictive accuracy alone does not establish whether a detector is appropriate for a particular cybersecurity setting. This article critically synthesizes fifteen peer-reviewed studies published during 2022–2026, together with authoritative authentication and e-mail security standards, to examine the applicability of conventional and artificial-intelligence-based phishing analysis and prevention techniques. A structured taxonomy distinguishes reputation and rule systems, lexical and structural URL analysis, e-mail semantics, sequence models, transformer architectures, ensembles, continual learning, and explainability mechanisms. This article introduces a context-aware applicability framework that separates minimum operational requirements from multi-criteria comparison of security efficacy, cross-source generalization, false-alarm burden, latency, resource cost, interpretability, dependency, maintainability, and preventive actionability. A reproducible evaluation protocol is specified for public URL and e-mail corpora, with safeguards against duplicate and domain leakage, temporal drift, misleading class prevalence, and incomplete end-to-end latency accounting. The evidence supports conditional rather than universal selection: inexpensive lexical models are attractive at browser and mobile endpoints; contextual text analysis adds value at e-mail gateways; and ensemble, adaptive, and explainable components are most useful when their operational overhead can be justified. The proposed defense-in-depth architecture couples detection to warnings, quarantine, phishing-resistant authentication, reporting, and incident response.

Keywords

Phishing; cyber threat intelligence; machine learning; deep learning; concept drift; security evaluation.

DOI : https://doi.org/10.5281/zenodo.23556037

Full Text:

Download Paper PDF

References

[1] H. Ghalechyan, E. Israyelyan, A. Arakelyan, G. Hovhannisyan, and A. Davtyan, “Phishing URL detection with neural networks: an empirical study,” Scientific Reports, vol. 14, art. no. 25134, 2024. doi: 10.1038/s41598-024-74725-6.

[2] R. S. Rao, C. Kondaiah, A. R. Pais, and B. Lee, “A hybrid super learner ensemble for phishing detection on mobile devices,” Scientific Reports, vol. 15, art. no. 16839, 2025. doi: 10.1038/s41598-025-02009-8.

[3] S. Abiramasundari and V. Ramaswamy, “Cacography based Ransomware Email Phishing Attack Prevention using Language Pack Tuned Transformer Language Model,” Scientific Reports, vol. 15, art. no. 21526, 2025. doi: 10.1038/s41598-025-06530-8.

[4] J. Zhou, K. Zhang, A. Bilal, et al., “An integrated CSPPC and BiLSTM framework for malicious URL detection,” Scientific Reports, vol. 15, art. no. 6659, 2025. doi: 10.1038/s41598-025-91148-z.

[5] M. Hosseinzadeh, U. Ali, S. Ali, et al., “Improving phishing email detection performance through deep learning with adaptive optimization,” Scientific Reports, vol. 15, art. no. 36724, 2025. doi: 10.1038/s41598-025-20668-5.

[6] A. Ejaz, A. N. Mian, and S. Manzoor, “Life-long phishing attack detection using continual learning,” Scientific Reports, vol. 13, art. no. 11488, 2023. doi: 10.1038/s41598-023-37552-9.

[7] D. Komosny, “Phishing detection on webpages in European non-English languages based on machine learning,” Scientific Reports, vol. 15, art. no. 37472, 2025. doi: 10.1038/s41598-025-21384-w.

[8] M. Dandotiya, N. K. Goyal, A. Khunteta, and B. Tiwari, “Real time identification of phishing attacks through machine learning enhanced browser extensions,” Scientific Reports, vol. 16, art. no. 6612, 2026. doi: 10.1038/s41598-026-35655-7.

[9] National Institute of Standards and Technology, “Digital Identity Guidelines: Authentication and Authenticator Management,” NIST SP 800-63B-4, July 2025. doi: 10.6028/NIST.SP.800-63b-4.

[10] E. Tabassi, “Artificial Intelligence Risk Management Framework (AI RMF 1.0),” NIST AI 100-1, Jan. 2023. doi: 10.6028/NIST.AI.100-1.

[11] T. Herr and J. Levine, Eds., “Domain-Based Message Authentication, Reporting, and Conformance (DMARC),” RFC 9989, May 2026. doi: 10.17487/RFC9989.

[12] Cybersecurity and Infrastructure Security Agency, “Implementing Phishing-Resistant MFA,” Fact Sheet, 2022. Available: https://www.cisa.gov/sites/default/files/2023-01/fact-sheet-implementing-phishing-resistant-mfa-508c.pdf.

[13] E. Gandotra, D. Gupta, M. Dhalaria, N. Gupta, and S. Redkar, “PhishDetect: A ranking-based classifier integration approach for improving phishing website detection,” Scientific Reports, vol. 16, art. no. 29386, 2026. doi: 10.1038/s41598-026-57807-5.

[14] M. Tawfik, A. A. Abu-Ein, A. H. Abdelhaliem, Y. M. Al-Sharo, and I. S. Fathi, “Explainable few-shot learning with modern BERT for detecting emerging phishing attacks using XF PhishBERT,” Scientific Reports, vol. 15, art. no. 42821, 2025. doi: 10.1038/s41598-025-27500-0.

[15] T. Kehkashan, M. Abdelhaq, A. S. Al-Shamayleh, et al., “Explainable phishing website detection for secure and sustainable cyber infrastructure,” Scientific Reports, vol. 15, art. no. 41751, 2025. doi: 10.1038/s41598-025-27984-w.

[16] J. C. Gomes de Barros et al., “Piracema: a Phishing snapshot database for building dataset features,” Scientific Reports, vol. 12, art. no. 15149, 2022. doi: 10.1038/s41598-022-19442-8.

[17] R. Rawat, H. Rawat, A. Rawat, and A. Rajavat, “An entropy-guided hybrid framework for real-time phishing detection in digital communication systems,” Scientific Reports, vol. 16, art. no. 17222, 2026. doi: 10.1038/s41598-026-46430-z.

[18] R. Gobinath and S. Manikandan, “Deep learning-based phishing classification framework for accurate detection using optimized URL intelligence,” Scientific Reports, vol. 16, art. no. 15794, 2026. doi: 10.1038/s41598-026-46481-2.

[19] B. B. Gupta, S.-H. Pan, A. Gaurav, et al., “Phishing threat mitigation in E-commerce using a quantum-enhanced hybrid AI framework,” Scientific Reports, vol. 15, art. no. 42282, 2025. doi: 10.1038/s41598-025-27515-7.

 

Share your valuable work from Social Media Buttons