Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems

Nikos Komninos; Warren Fernando

arxiv: 2606.11471 · v1 · pith:TTFQWYFInew · submitted 2026-06-09 · 💻 cs.CR · cs.LG

Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems

Warren Fernando , Nikos Komninos This is my paper

Pith reviewed 2026-06-27 12:16 UTC · model grok-4.3

classification 💻 cs.CR cs.LG

keywords concept driftphishing detectionmachine learningspam emailsemail securitycybersecurityadversarial evolution

0 comments

The pith

Evolution in spam emails causes concept drift that degrades machine learning phishing detectors.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out to establish that changes over time in the characteristics of spam and phishing emails produce concept drift, which reduces the effectiveness of machine learning models trained to detect them. A sympathetic reader would care because phishing remains a primary entry point for malware attacks, so any systematic loss of detector performance directly increases user exposure. The work focuses on email as the domain where this evolution occurs and plans to evaluate the resulting degradation while testing ways to limit it.

Core claim

The evolution within the spam email domain impacts the performance of machine learning-based detection systems, and strategies can be explored for mitigating associated performance degradation.

What carries the argument

Concept drift arising from the changing statistical properties of spam and phishing emails, which creates a mismatch between training data and new messages seen by deployed models.

If this is right

Machine learning models trained on historical spam data will show declining accuracy on newer phishing attempts.
Periodic model retraining or adaptive learning methods become necessary to restore performance.
Email security pipelines must incorporate mechanisms to detect and respond to domain evolution.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same drift mechanism is likely to affect machine learning detectors in related domains such as malware classification.
Continuous performance monitoring against live email traffic would be a direct practical next step.
Feature sets that are more invariant to attacker evolution could reduce the frequency of required updates.

Load-bearing premise

That measurable concept drift occurs in the phishing domain and produces clear performance degradation in standard machine learning models.

What would settle it

A time-series experiment that trains fixed machine learning models on older phishing data and measures their detection rates on progressively newer emails, showing no accuracy drop.

Figures

Figures reproduced from arXiv: 2606.11471 by Nikos Komninos, Warren Fernando.

**Figure 1.** Figure 1: Detection framework of the underlying algorithm. The research proposed in [22] uses a hybrid machine-learning approach to detect phishing URLs and achieves promising results using the Microsoft Kaggle dataset. In terms of concept drift research for phishing, there are some prominent research studies which attempt to address concept drift. The research explored in [23] uses Autoencoders to increase the dete… view at source ↗

read the original abstract

The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent channels. The proliferation of email communication is apparent in both professional and personal contexts, thereby creating numerous vulnerabilities for malicious actors to exploit. Spam emails, a form of unsolicited correspondence often bearing malicious intent towards recipients, have been an ongoing challenge for email users since the inception of email technology, and this problem has been exacerbated by the growth of the digital landscape. Email spam filters are integral components of email clients, engineered to identify potentially harmful messages and alert users to their malicious content. Phishing, frequently the initial phase of malware-based attacks, is evolving rapidly, with malware becoming increasingly sophisticated over time. A widely adopted approach for detecting malicious activity within malware and spam domains is the application of machine learning. Our aim is to assess the impact of the evolution within the spam email domain on these machine learning-based detection systems and to explore strategies for mitigating associated performance degradation.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This paper states an intent to evaluate concept drift in ML phishing detectors and explore mitigations, but the text contains only the abstract with no datasets, methods, results, or metrics.

read the letter

This paper's main point is to look at how changes in spam and phishing over time hurt machine learning detectors and to try out ways to reduce that drop in performance. That's a reasonable practical question in security.

What stands out is the focus on the spam email domain specifically. The authors note that phishing is getting more sophisticated, which is accurate, and they want to see the impact on ML systems. They also mention exploring mitigation strategies, which could be helpful if done right.

The problem is that nothing in the text shows any actual evaluation. There's no mention of datasets, whether they used time-based splits to simulate drift, what models they tested, or any metrics like accuracy drop or drift measures. Without that, it's impossible to know if drift is a big issue here or if the fixes work. The claims rest on the assumption that evolution causes measurable degradation, but there's no evidence presented.

This feels like it could be for people working on ML in cybersecurity who are already aware of drift but want a phishing-specific case study. However, as it stands, the work doesn't provide enough to be useful or citable.

I wouldn't bring it to a reading group or cite it. It probably shouldn't go to peer review in this form because the central evaluation is missing. If the full paper has the experiments with clear results, that changes things, but based on what's here, it's not ready.

Referee Report

2 major / 1 minor

Summary. The manuscript claims that the evolution within the spam email domain impacts the performance of machine learning-based detection systems and that strategies can be explored for mitigating associated performance degradation due to concept drift in phishing detection.

Significance. If the results hold, the work would address a practically important issue in cybersecurity, where phishing remains a leading attack vector and static ML detectors are known to degrade over time in adversarial settings. Quantifying drift effects and validating mitigations could inform more robust detection pipelines.

major comments (2)

[Abstract / Manuscript body] Abstract and overall manuscript: The central claim requires empirical demonstration via time-ordered datasets, drift quantification (e.g., via Hellinger distance or ADWIN), statistically significant performance drops (accuracy/F1 on future vs. past test sets), and at least one evaluated mitigation, but no datasets, temporal splits, models, metrics, or results are provided anywhere in the text.
[Methods / Experiments] Methods and evaluation (absent): No description of feature sets, ML algorithms, evaluation protocol, or mitigation approaches (e.g., online learning, drift detection triggers) is given, preventing assessment of whether observed degradation is due to concept drift rather than label shift or other confounds.

minor comments (1)

[Abstract] Abstract: The opening sentences are somewhat repetitive regarding the growth of digital communication and email; tightening would improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive review. We acknowledge that the submitted manuscript consists primarily of a high-level motivation and statement of aims without the empirical components, datasets, methods, or results needed to substantiate the central claims about concept drift in phishing detection. We will revise the manuscript to incorporate the required elements.

read point-by-point responses

Referee: [Abstract / Manuscript body] Abstract and overall manuscript: The central claim requires empirical demonstration via time-ordered datasets, drift quantification (e.g., via Hellinger distance or ADWIN), statistically significant performance drops (accuracy/F1 on future vs. past test sets), and at least one evaluated mitigation, but no datasets, temporal splits, models, metrics, or results are provided anywhere in the text.

Authors: We agree that the current manuscript does not contain the requested empirical demonstration. The provided text is limited to the abstract and motivation. In revision we will add time-ordered datasets with explicit temporal splits, drift quantification (including Hellinger distance and ADWIN), statistical tests on performance degradation (accuracy/F1 on future versus past sets), and evaluation of at least one mitigation strategy. revision: yes
Referee: [Methods / Experiments] Methods and evaluation (absent): No description of feature sets, ML algorithms, evaluation protocol, or mitigation approaches (e.g., online learning, drift detection triggers) is given, preventing assessment of whether observed degradation is due to concept drift rather than label shift or other confounds.

Authors: We concur that the methods and evaluation sections are absent. The revised manuscript will include detailed descriptions of feature sets, ML algorithms, the temporal evaluation protocol, mitigation approaches (online learning, drift detection triggers), and explicit discussion of potential confounds such as label shift to isolate concept drift effects. revision: yes

Circularity Check

0 steps flagged

No derivation chain or equations present; empirical claim shows no circularity.

full rationale

The supplied abstract and description contain only a high-level research aim to assess concept drift impact on ML phishing detectors and explore mitigations, with no equations, fitted parameters, predictions, self-citations, or uniqueness theorems invoked. No load-bearing step reduces to its own inputs by construction, as there is no mathematical derivation or renamed empirical pattern at all. This is the common case of a non-circular empirical proposal whose validity depends on future experiments rather than internal self-reference.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no free parameters, axioms, or invented entities are described.

pith-pipeline@v0.9.1-grok · 5701 in / 970 out tokens · 14937 ms · 2026-06-27T12:16:01.925337+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

33 extracted references · 22 canonical work pages

[1]

R. Chen, J. Gaia, and H. R. Rao, ”An examination of the effect of recent phishing encounters on phishing susceptibility,” Decis. Support Syst., 2020, doi: 10.1016/j.dss.2020.113287

work page doi:10.1016/j.dss.2020.113287 2020
[2]

Patil and S

S. Patil and S. Dhage, ”A Methodical Overview on Phishing Detection along with an Orga- nized Way to Construct an Anti-Phishing Framework,” 2019 5th International Conference on Ad- vanced Computing & Communication Systems (ICACCS), Coimbatore, India, 2019, pp. 588-593, doi: 10.1109/ICACCS.2019.8728356

work page doi:10.1109/icaccs.2019.8728356 2019
[3]

Available online: https://www.thesslstore.com/blog/phishing-statistic/

C.Crane, ”Phishing Statistics: The 21 Latest Phishing Stats you need to know in 2024, 2024. Available online: https://www.thesslstore.com/blog/phishing-statistic/

2024
[4]

Cofence email security, ”The history of Phishing”, 2024 Available online: https://cofense.com/knowledge-center/history-of-phishing

2024
[6]

6. D.W. Fernando, N. Komninos, FeSAD ransomware detection framework with machine learning using adaption to concept drift, Computers & Security, Volume 137, 2024, 103629, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2023.103629

work page doi:10.1016/j.cose.2023.103629 2024
[8]

Kosmopoulos, G

A. Kosmopoulos, G. Paliouras, and I. Androutsopoulos, ”Adaptive spam filtering using only na¨ ıve bayes text classifiers,” In Proceedings of the Conference on Email and Anti-Spam, 2008

2008
[9]

Saraswat and M

P. Saraswat and M. Singh Solanki, ”Phishing Detection in Emails using Machine Learning,” 2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, 2022, pp. 420-424, doi: 10.1109/ICTACS56270.2022.9987839. 22

work page doi:10.1109/ictacs56270.2022.9987839 2022
[10]

I. Saha, D. Sarma, R. J. Chakma, M. N. Alam, A. Sultana and S. Hossain, ”Phishing Attacks Detection using Deep Learning Approach,” 2020 Third International Conference on Smart Sys- tems and Inventive Technology (ICSSIT), Tirunelveli, India, 2020, pp. 1180-1185, doi: 10.1109/IC- SSIT48917.2020.9214132

work page doi:10.1109/ic- 2020
[11]

M. R. Ridho and H. H. Nuha, ”Application of Extreme Learning Machine (ELM) Classification in Detecting Phishing Sites,” 2022 5th International Conference of Computer and Informatics Engineering (IC2IE), Jakarta, Indonesia, 2022, pp. 60-64, doi: 10.1109/IC2IE56416.2022.9970191

work page doi:10.1109/ic2ie56416.2022.9970191 2022
[12]

Lakshmanarao, P

A. Lakshmanarao, P. S. P. Rao and M. M. B. Krishna, ”Phishing website detection using novel machine learning fusion approach,” 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, 2021, pp. 1164-1169, doi: 10.1109/ICAIS50930.2021.9395810

work page doi:10.1109/icais50930.2021.9395810 2021
[13]

13. I. Ortiz Garc´ es, M. F. Cazares and R. O. Andrade, ”Detection of Phishing Attacks with Machine Learning Techniques in Cognitive Security Architecture,” 2019 International Conference on Computa- tional Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2019, pp. 366-370, doi: 10.1109/CSCI49370.2019.00071

work page doi:10.1109/csci49370.2019.00071 2019
[14]

14. H. Bouijij and A. Berqia, ”Machine Learning Algorithms Evaluation for Phishing URLs Classifi- cation,” 2021 4th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Alkhobar, Saudi Arabia, 2021, pp. 01-05, doi: 10.1109/ISAECT53699.2021.9668489

work page doi:10.1109/isaect53699.2021.9668489 2021
[15]

Chandra, Gregorius, M

A. Chandra, Gregorius, M. S. J. Immanuel, A. A. S. Gunawan and Anderies, ”Accuracy Comparison of Different Machine Learning Models in Phishing Detection,” 2022 5th International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia, 2022, pp. 24-29, doi: 10.1109/ICOIACT55506.2022.9972107

work page doi:10.1109/icoiact55506.2022.9972107 2022
[16]

Bagui, D

S. Bagui, D. Nandi, S. Bagui and R. J. White, ”Classifying Phishing Email Using Machine Learn- ing and Deep Learning,” 2019 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Oxford, UK, 2019, pp. 1-2, doi: 10.1109/CyberSecPODS.2019.8885143

work page doi:10.1109/cybersecpods.2019.8885143 2019
[17]

Chinnasamy, N

P. Chinnasamy, N. Kumaresan, R. Selvaraj, S. Dhanasekaran, K. Ramprathap and S. Boddu, ”An Efficient Phishing Attack Detection using Machine Learning Algorithms,” 2022 International Confer- ence on Advancements in Smart, Secure and Intelligent Computing (ASSIC), Bhubaneswar, India, 2022, pp. 1-6, doi: 10.1109/ASSIC55218.2022.10088399

work page doi:10.1109/assic55218.2022.10088399 2022
[18]

Anakal, K

S. Anakal, K. Maka, A. Tadkal, S. Humanabad, S. Anakal and E. Laxmikant, ”Phishing Website Detection Using Machine Learning Methods,” 2023 International Conference on Integrated Intelli- gence and Communication Systems (ICIICS), Kalaburagi, India, 2023, pp. 1-5, doi: 10.1109/ICI- ICS59993.2023.10420933

work page doi:10.1109/ici- 2023
[19]

Uplenchwar, V

S. Uplenchwar, V. Sawant, P. Surve, S. Deshpande and S. Kelkar, ”Phishing Attack Detection on Text Messages Using Machine Learning Techniques,” 2022 IEEE Pune Section International Conference (PuneCon), Pune, India, 2022, pp. 1-5, doi: 10.1109/PuneCon55413.2022.10014876

work page doi:10.1109/punecon55413.2022.10014876 2022
[20]

Bostoganashvili, The Whys and How of Email Spam Filters, 2024, Available online: https://mailtrap.io/blog/spam-filters/

K. Bostoganashvili, The Whys and How of Email Spam Filters, 2024, Available online: https://mailtrap.io/blog/spam-filters/

2024
[21]

Jordaney, K

R. Jordaney, K. Sharad, S. Kumar Dash, Z. Wang, D. Papini, I. Nouretdinov, and L. Cavallaro, 2017, ”Transcend: detecting concept drift in malware classification models”, In Proceedings of the 26th USENIX Conference on Security Symposium (SEC’17), USENIX Association, USA, 625–642

2017
[22]

Karim, M

A. Karim, M. Shahroz, K. Mustofa, S.B. Belhaouri, R. Kumar Joga, ”Phishing Detection System Through Hybrid Machine Learning Based on URL”, 2023, IEEE Access volume 11, pp. 36805-36822

2023
[23]

Menon, G

A.G. Menon, G. Gressel, S.M. Thampi, S. Piramuthu, KC Lee, S. Berretti, M. Wozniak, M. Singh, 2021, ”Concept Drift Detection in Phishing Using Autoencoders. In Machine Learning and Meta- heuristics Algorithms and Applications. SoMMA 2020. Communications in Computer and Information Science, vol 1366. Springer, Singapore. 23

2021
[24]

Zi Hayat, J

M. Zi Hayat, J. Basiri, L. Seyedhossein and A. Shakery, ”Content-based concept drift detection for Email spam filtering,” 2010 5th International Symposium on Telecommunications, Tehran, Iran, 2010, pp. 531-536, doi: 10.1109/ISTEL.2010.5734082

work page doi:10.1109/istel.2010.5734082 2010
[25]

Fernando and N

D.W. Fernando and N. Komninos,FeSA: Feature selection architecture for ransomware detection under concept drift, Computers & Security Volume 116, 2022

2022
[26]

Mamun, M.A

M.S.I. Mamun, M.A. Rathore, A.H. Lashkari, N. Stakhanova and A.A. Ghorbani, ”Detecting Mali- cious URLs Using Lexical Analysis”, Network and System Security, Springer International Publishing, pp. 467-482, 2016

2016
[27]

2024, Available online: https://github.com/JPCERTCC/phishurl-list

JPCERTCC, JPCERTCC Phishing Dataset, 2019. 2024, Available online: https://github.com/JPCERTCC/phishurl-list

2019
[28]

Ariyadasa, S

S. Ariyadasa, S. Fernando, S. Fernando, 2021, Phishing Websites Dataset, Mendeley Data, V1, doi: 10.17632/n96ncsr5g4.1

work page doi:10.17632/n96ncsr5g4.1 2021
[29]

Arthi , 2024, Phishing URL dataset, Mendeley Data, V1, doi: 10.17632/vfszbj9b36.1

K.S SKAITHOLIKKAL, JISHNU, B. Arthi , 2024, Phishing URL dataset, Mendeley Data, V1, doi: 10.17632/vfszbj9b36.1

work page doi:10.17632/vfszbj9b36.1 2024
[30]

S.S. Shafin, An explainable feature selection framework for web phishing detection with machine learning, Data Science and Management, Volume 8, Issue 2,2025, Pages 127-136, ISSN 2666-7649, https://doi.org/10.1016/j.dsm.2024.08.004

work page doi:10.1016/j.dsm.2024.08.004 2025
[31]

Ahmed , I.M

T.M. Ahmed , I.M. Kabirul , B. Touhid , S. Abdus , Dataset of suspicious phishing URL detection, Frontiers in Computer Science, Volume 6 - 2024, 2024, DOI=10.3389/fcomp.2024.1308634

work page doi:10.3389/fcomp.2024.1308634 2024
[32]

Tan (2018), ”Phishing Dataset for Machine Learning: Feature Evaluation”, Mendeley Data, V1, doi: 10.17632/h3cgnj8hft.1

C.L. Tan (2018), ”Phishing Dataset for Machine Learning: Feature Evaluation”, Mendeley Data, V1, doi: 10.17632/h3cgnj8hft.1

work page doi:10.17632/h3cgnj8hft.1 2018
[33]

Vrbanˇ ciˇ c, I

G. Vrbanˇ ciˇ c, I. Jr. Fister, V. Podgorelec, Datasets for Phishing Websites Detection. Data in Brief, Vol. 33, 2020, DOI: 10.1016/j.dib.2020.106438

work page doi:10.1016/j.dib.2020.106438 2020
[34]

Hannousse S

A. Hannousse S. Yahiouche, (2020), ”Web page phishing detection”, Mendeley Data, V1, doi: 10.17632/c2gw7fy2j4.1

work page doi:10.17632/c2gw7fy2j4.1 2020
[35]

D.W.A. Fernando (2023) ”FeSAD: Ransomware Detection with Ma- chine learning using Adaption to Concept Drift” Available Online: https://openaccess.city.ac.uk/id/eprint/32739/1/Fernando%20thesis%202023%20PDF-A.pdf 24 Damien Warren Fernandoreceived a MSci in Computer Sci- ence and Cyber Security in 2017 from City, University of Lon- don. Having worked at Cit...

2023

[1] [1]

R. Chen, J. Gaia, and H. R. Rao, ”An examination of the effect of recent phishing encounters on phishing susceptibility,” Decis. Support Syst., 2020, doi: 10.1016/j.dss.2020.113287

work page doi:10.1016/j.dss.2020.113287 2020

[2] [2]

Patil and S

S. Patil and S. Dhage, ”A Methodical Overview on Phishing Detection along with an Orga- nized Way to Construct an Anti-Phishing Framework,” 2019 5th International Conference on Ad- vanced Computing & Communication Systems (ICACCS), Coimbatore, India, 2019, pp. 588-593, doi: 10.1109/ICACCS.2019.8728356

work page doi:10.1109/icaccs.2019.8728356 2019

[3] [3]

Available online: https://www.thesslstore.com/blog/phishing-statistic/

C.Crane, ”Phishing Statistics: The 21 Latest Phishing Stats you need to know in 2024, 2024. Available online: https://www.thesslstore.com/blog/phishing-statistic/

2024

[4] [4]

Cofence email security, ”The history of Phishing”, 2024 Available online: https://cofense.com/knowledge-center/history-of-phishing

2024

[5] [6]

6. D.W. Fernando, N. Komninos, FeSAD ransomware detection framework with machine learning using adaption to concept drift, Computers & Security, Volume 137, 2024, 103629, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2023.103629

work page doi:10.1016/j.cose.2023.103629 2024

[6] [8]

Kosmopoulos, G

A. Kosmopoulos, G. Paliouras, and I. Androutsopoulos, ”Adaptive spam filtering using only na¨ ıve bayes text classifiers,” In Proceedings of the Conference on Email and Anti-Spam, 2008

2008

[7] [9]

Saraswat and M

P. Saraswat and M. Singh Solanki, ”Phishing Detection in Emails using Machine Learning,” 2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, 2022, pp. 420-424, doi: 10.1109/ICTACS56270.2022.9987839. 22

work page doi:10.1109/ictacs56270.2022.9987839 2022

[8] [10]

I. Saha, D. Sarma, R. J. Chakma, M. N. Alam, A. Sultana and S. Hossain, ”Phishing Attacks Detection using Deep Learning Approach,” 2020 Third International Conference on Smart Sys- tems and Inventive Technology (ICSSIT), Tirunelveli, India, 2020, pp. 1180-1185, doi: 10.1109/IC- SSIT48917.2020.9214132

work page doi:10.1109/ic- 2020

[9] [11]

M. R. Ridho and H. H. Nuha, ”Application of Extreme Learning Machine (ELM) Classification in Detecting Phishing Sites,” 2022 5th International Conference of Computer and Informatics Engineering (IC2IE), Jakarta, Indonesia, 2022, pp. 60-64, doi: 10.1109/IC2IE56416.2022.9970191

work page doi:10.1109/ic2ie56416.2022.9970191 2022

[10] [12]

Lakshmanarao, P

A. Lakshmanarao, P. S. P. Rao and M. M. B. Krishna, ”Phishing website detection using novel machine learning fusion approach,” 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, 2021, pp. 1164-1169, doi: 10.1109/ICAIS50930.2021.9395810

work page doi:10.1109/icais50930.2021.9395810 2021

[11] [13]

13. I. Ortiz Garc´ es, M. F. Cazares and R. O. Andrade, ”Detection of Phishing Attacks with Machine Learning Techniques in Cognitive Security Architecture,” 2019 International Conference on Computa- tional Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2019, pp. 366-370, doi: 10.1109/CSCI49370.2019.00071

work page doi:10.1109/csci49370.2019.00071 2019

[12] [14]

14. H. Bouijij and A. Berqia, ”Machine Learning Algorithms Evaluation for Phishing URLs Classifi- cation,” 2021 4th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Alkhobar, Saudi Arabia, 2021, pp. 01-05, doi: 10.1109/ISAECT53699.2021.9668489

work page doi:10.1109/isaect53699.2021.9668489 2021

[13] [15]

Chandra, Gregorius, M

A. Chandra, Gregorius, M. S. J. Immanuel, A. A. S. Gunawan and Anderies, ”Accuracy Comparison of Different Machine Learning Models in Phishing Detection,” 2022 5th International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia, 2022, pp. 24-29, doi: 10.1109/ICOIACT55506.2022.9972107

work page doi:10.1109/icoiact55506.2022.9972107 2022

[14] [16]

Bagui, D

S. Bagui, D. Nandi, S. Bagui and R. J. White, ”Classifying Phishing Email Using Machine Learn- ing and Deep Learning,” 2019 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Oxford, UK, 2019, pp. 1-2, doi: 10.1109/CyberSecPODS.2019.8885143

work page doi:10.1109/cybersecpods.2019.8885143 2019

[15] [17]

Chinnasamy, N

P. Chinnasamy, N. Kumaresan, R. Selvaraj, S. Dhanasekaran, K. Ramprathap and S. Boddu, ”An Efficient Phishing Attack Detection using Machine Learning Algorithms,” 2022 International Confer- ence on Advancements in Smart, Secure and Intelligent Computing (ASSIC), Bhubaneswar, India, 2022, pp. 1-6, doi: 10.1109/ASSIC55218.2022.10088399

work page doi:10.1109/assic55218.2022.10088399 2022

[16] [18]

Anakal, K

S. Anakal, K. Maka, A. Tadkal, S. Humanabad, S. Anakal and E. Laxmikant, ”Phishing Website Detection Using Machine Learning Methods,” 2023 International Conference on Integrated Intelli- gence and Communication Systems (ICIICS), Kalaburagi, India, 2023, pp. 1-5, doi: 10.1109/ICI- ICS59993.2023.10420933

work page doi:10.1109/ici- 2023

[17] [19]

Uplenchwar, V

S. Uplenchwar, V. Sawant, P. Surve, S. Deshpande and S. Kelkar, ”Phishing Attack Detection on Text Messages Using Machine Learning Techniques,” 2022 IEEE Pune Section International Conference (PuneCon), Pune, India, 2022, pp. 1-5, doi: 10.1109/PuneCon55413.2022.10014876

work page doi:10.1109/punecon55413.2022.10014876 2022

[18] [20]

Bostoganashvili, The Whys and How of Email Spam Filters, 2024, Available online: https://mailtrap.io/blog/spam-filters/

K. Bostoganashvili, The Whys and How of Email Spam Filters, 2024, Available online: https://mailtrap.io/blog/spam-filters/

2024

[19] [21]

Jordaney, K

R. Jordaney, K. Sharad, S. Kumar Dash, Z. Wang, D. Papini, I. Nouretdinov, and L. Cavallaro, 2017, ”Transcend: detecting concept drift in malware classification models”, In Proceedings of the 26th USENIX Conference on Security Symposium (SEC’17), USENIX Association, USA, 625–642

2017

[20] [22]

Karim, M

A. Karim, M. Shahroz, K. Mustofa, S.B. Belhaouri, R. Kumar Joga, ”Phishing Detection System Through Hybrid Machine Learning Based on URL”, 2023, IEEE Access volume 11, pp. 36805-36822

2023

[21] [23]

Menon, G

A.G. Menon, G. Gressel, S.M. Thampi, S. Piramuthu, KC Lee, S. Berretti, M. Wozniak, M. Singh, 2021, ”Concept Drift Detection in Phishing Using Autoencoders. In Machine Learning and Meta- heuristics Algorithms and Applications. SoMMA 2020. Communications in Computer and Information Science, vol 1366. Springer, Singapore. 23

2021

[22] [24]

Zi Hayat, J

M. Zi Hayat, J. Basiri, L. Seyedhossein and A. Shakery, ”Content-based concept drift detection for Email spam filtering,” 2010 5th International Symposium on Telecommunications, Tehran, Iran, 2010, pp. 531-536, doi: 10.1109/ISTEL.2010.5734082

work page doi:10.1109/istel.2010.5734082 2010

[23] [25]

Fernando and N

D.W. Fernando and N. Komninos,FeSA: Feature selection architecture for ransomware detection under concept drift, Computers & Security Volume 116, 2022

2022

[24] [26]

Mamun, M.A

M.S.I. Mamun, M.A. Rathore, A.H. Lashkari, N. Stakhanova and A.A. Ghorbani, ”Detecting Mali- cious URLs Using Lexical Analysis”, Network and System Security, Springer International Publishing, pp. 467-482, 2016

2016

[25] [27]

2024, Available online: https://github.com/JPCERTCC/phishurl-list

JPCERTCC, JPCERTCC Phishing Dataset, 2019. 2024, Available online: https://github.com/JPCERTCC/phishurl-list

2019

[26] [28]

Ariyadasa, S

S. Ariyadasa, S. Fernando, S. Fernando, 2021, Phishing Websites Dataset, Mendeley Data, V1, doi: 10.17632/n96ncsr5g4.1

work page doi:10.17632/n96ncsr5g4.1 2021

[27] [29]

Arthi , 2024, Phishing URL dataset, Mendeley Data, V1, doi: 10.17632/vfszbj9b36.1

K.S SKAITHOLIKKAL, JISHNU, B. Arthi , 2024, Phishing URL dataset, Mendeley Data, V1, doi: 10.17632/vfszbj9b36.1

work page doi:10.17632/vfszbj9b36.1 2024

[28] [30]

S.S. Shafin, An explainable feature selection framework for web phishing detection with machine learning, Data Science and Management, Volume 8, Issue 2,2025, Pages 127-136, ISSN 2666-7649, https://doi.org/10.1016/j.dsm.2024.08.004

work page doi:10.1016/j.dsm.2024.08.004 2025

[29] [31]

Ahmed , I.M

T.M. Ahmed , I.M. Kabirul , B. Touhid , S. Abdus , Dataset of suspicious phishing URL detection, Frontiers in Computer Science, Volume 6 - 2024, 2024, DOI=10.3389/fcomp.2024.1308634

work page doi:10.3389/fcomp.2024.1308634 2024

[30] [32]

Tan (2018), ”Phishing Dataset for Machine Learning: Feature Evaluation”, Mendeley Data, V1, doi: 10.17632/h3cgnj8hft.1

C.L. Tan (2018), ”Phishing Dataset for Machine Learning: Feature Evaluation”, Mendeley Data, V1, doi: 10.17632/h3cgnj8hft.1

work page doi:10.17632/h3cgnj8hft.1 2018

[31] [33]

Vrbanˇ ciˇ c, I

G. Vrbanˇ ciˇ c, I. Jr. Fister, V. Podgorelec, Datasets for Phishing Websites Detection. Data in Brief, Vol. 33, 2020, DOI: 10.1016/j.dib.2020.106438

work page doi:10.1016/j.dib.2020.106438 2020

[32] [34]

Hannousse S

A. Hannousse S. Yahiouche, (2020), ”Web page phishing detection”, Mendeley Data, V1, doi: 10.17632/c2gw7fy2j4.1

work page doi:10.17632/c2gw7fy2j4.1 2020

[33] [35]

D.W.A. Fernando (2023) ”FeSAD: Ransomware Detection with Ma- chine learning using Adaption to Concept Drift” Available Online: https://openaccess.city.ac.uk/id/eprint/32739/1/Fernando%20thesis%202023%20PDF-A.pdf 24 Damien Warren Fernandoreceived a MSci in Computer Sci- ence and Cyber Security in 2017 from City, University of Lon- don. Having worked at Cit...

2023