A CONCEPT-DRIFT-AWARE ADAPTIVE MACHINE LEARNING FRAMEWORK FOR PHISHING ATTACK DETECTION
DOI:
https://doi.org/10.62373/12d6r307Keywords:
Keywords: PHISHING ,, ADAPTIVE MACHINE LEARNING, CONCEPT DRIFT HANDLING, EMAIL SECURITY, CYBER THREAT INTELLIGENCEAbstract
Consequently, phishing attacks remain increasingly sophisticated, creating major risk threats to various stakeholders,
particularly with the changing dynamics of cybersecurity. Traditional static machine learning techniques have been challenged
to sustain accuracy after a period of application, given their low adaptability to updated phishing attack scenarios, resulti ng
from the occurrence of concept drift. This paper presents the design of a proposed model for an adaptive machine learning
algorithm for phishing detection, which includes incremental learning strategies for detecting phishing attacks. The proposed
model for incremental learning has been tested based on its application to various benchmark public phishing datasets.
Experimental results of the proposed model show improvements of 2-5% for detecting phishing attacks, with a reduction of
false positives.
Downloads
References
[1]D. Čatloch, E. Chovancová, M. Chovanec, et al., “Application of machine learning algorithms for cybersecurity: Detection
and classification of malware, DDoS, and phishing attacks,” in Proc. IEEE 29th Int. Conf. Intelligent Engineering Systems
(INES 2025), Palermo, Italy, June 2025, pp. 353–358.
[2]N. Nithya and S. Sakthimuneeswaran, “Combined approach using multiattention graph convolution network towards
prevention, detection and classification of phishing attack,” in Proc. 2nd Int. Conf. New Frontiers in Communication,
Automation, Management and Security (ICCAMS 2025), 2025, pp. 1–6.
[3]S. Alqahtani and P. Nanda, “Effects of personal characteristics on phishing awareness, anti-phishing tool usage, and
phishing avoidance behavior: A structural equation modeling approach,” in Proc. IEEE Int. Conf. Security of Information and
Networks, 2024, pp. 1–8.
[4]M. Ahsan, K. E. Nygard, R. Gomes, et al., “Cybersecurity threats and their mitigation approaches using machine
learning—A review,” Journal of Cybersecurity and Privacy, vol. 2, no. 3, pp. 527–555, 2022.
[5] O. A. Aslan and R. Samet, “A comprehensive review on malware detection approaches,” IEEE Access, vol. 8, pp. 6249
6271, 2020.
[6] T. E. Ali, Y.-W. Chong, and S. Manickam, “Machine learning techniques to detect a DDoS attack in SDN: A systematic
review,” Applied Sciences, vol. 13, no. 5, p. 3183, 2023.
[7] M. A. Ferrag, L. Maglaras, S. Moschoyiannis, et al., “Deep learning for cybersecurity intrusion detection: Approaches,
datasets, and comparative study,” Journal of Information Security and Applications, vol. 50, p. 102419, 2020.
[8] R. K. Mbura, A. K. Benedicto, and R. Sinde, “A Novel Hybrid Approach for Identification of Discriminative Features in
Phishing Emails,” IEEE Access,
vol.
14,
2026, doi: 10.1109/ACCESS.2025.3649636.
[9] A. S. K. Joseph and S. Srinivasan, “Anti-Phishing Adaptive AI Systems: Efficiently Countering Social Engineering
Attacks by Real-Time Analysis of Email Content,” in Proc. 2025 Int. Conf. Computational Innovations and Engineering
Sustainability (ICCIES), 2025.
[10] A. Kafi, S. Saha, and N. Shahriar, “Weighted Reciprocal Rank Fusion RAG for Context-Aware DoS Attack Mitigation,”
in Proc. 2026 IEEE 23rd Consumer Communications & Networking Conf. (CCNC), 2026.
Downloads
Published
Data Availability Statement
NA
Issue
Section
License
Copyright (c) 2026 Yogesvari Joshi, Dhiren Purohit (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in PUXplore: Multidisciplinary Journal of Engineering are licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license.
Under this license, anyone may read, download, copy, distribute, and share the work for non-commercial purposes, provided that appropriate credit is given to the author(s), the journal, and a link to the license is included.
No adaptations, derivatives, or modifications of the work are permitted without prior written permission from the copyright holder.
Authors retain copyright and grant the journal the right of first publication under this license.
