Robust Explainable and Calibrated Machine Learning for Phishing URL Detection under Constrained Feature Perturbations
DOI:
https://doi.org/10.68307/a3mqv686Keywords:
phishing detection, trustworthy artificial intelligence, calibration, explainable artificial intelligence, adversarial robustness, SHAP, domain grouped evaluationAbstract
Phishing detectors can achieve high benchmark accuracy while remaining vulnerable to feature manipulation and difficult to assess as trustworthy decision systems; this study evaluates leakage controlled discrimination calibration explanation stability and constrained adversarial robustness on the PhiUSIIL dataset through a normalized domain grouped development protocol and one frozen test assessment; five model families were compared under conservative and full sensitivity feature conditions while calibration permutation importance Tree SHAP explanations and greedy feature space evasion were analysed; conservative uncalibrated HistGradientBoosting achieved locked test recall of 0.999897 F1 of 0.999949 and Brier score of 0.000041 although attack success reached 0.7042 at three changes and 0.8462 at five changes while mean SHAP cosine similarity fell to minus 0.350; the study also presents a six layer operational architecture that connects evidence governance prediction explanation robustness controls and monitoring; the evidence shows that clean grouped performance and probability reliability can coexist with severe representation level vulnerability and therefore phishing model evaluation should report predictive calibration explanation architectural and adversarial evidence together.
References
[1] Arvind Prasad and Shalini Chandra. PhiUSIIL A Diverse Security Profile Empowered Phishing URL Detection Framework Based on Similarity Index and Incremental Learning. Computers and Security. 2024. 10.1016/j.cose.2023.103545.
[2] Ozgur Koray Sahingoz and Ebubekir Buber and Onder Demir and Banu Diri. Machine Learning Based Phishing Detection from URLs. Expert Systems with Applications. 2019. 10.1016/j.eswa.2018.09.029.
[3] Ammara Zamir and Hikmat Ullah Khan and Tassawar Iqbal and Nazish Yousaf and Farah Aslam and Almas Anjum and Maryam Hamdani. Phishing Web Site Detection Using Diverse Machine Learning Algorithms. The Electronic Library. 2020. 10.1108/EL-05-2019-0118.
[4] Yukun Li and Zhenguo Yang and Xu Chen and Huaping Yuan and Wenyin Liu. A Stacking Model Using URL and HTML Features for Phishing Webpage Detection. Future Generation Computer Systems. 2019. 10.1016/j.future.2018.11.004.
[5] Brij B Gupta and Krishna Yadav and Imran Razzak and Konstantinos Psannis and Arcangelo Castiglione and Xiaojun Chang. A Novel Approach for Phishing URLs Detection Using Lexical Based Machine Learning in a Real Time Environment. Computer Communications. 2021. 10.1016/j.comcom.2021.04.023.
[6] Dong Jie Liu and Guang Gang Geng and Xiao Bo Jin and Wei Wang. An Efficient Multistage Phishing Website Detection Model Based on the CASE Feature Framework Aiming at the Real Web Environment. Computers and Security. 2021. 10.1016/j.cose.2021.102421.
[7] Wei Wei and Qiao Ke and Jakub Nowak and Marcin Korytkowski and Rafal Scherer and Marcin Wozniak. Accurate and Fast URL Phishing Detector A Convolutional Neural Network Approach. Computer Networks. 2020. 10.1016/j.comnet.2020.107275.
[8] Xi Xiao and Dianyan Zhang and Guangwu Hu and Yong Jiang and Shutao Xia. CNN MHSA A Convolutional Neural Network and Multi Head Self Attention Combined Approach for Detecting Phishing Websites. Neural Networks. 2020. 10.1016/j.neunet.2020.02.013.
[9] Farid Tajaddodianfar and Jack W Stokes and Arun Gururajan. Texception A Character Word Level Deep Learning Model for Phishing URL Detection. IEEE ICASSP. 2020. 10.1109/ICASSP40776.2020.9053670.
[10] Ayman El Aassal and Shahryar Baki and Avisha Das and Rakesh Verma. An In Depth Benchmarking and Evaluation of Phishing Detection Research for Security Needs. IEEE Access. 2020. 10.1109/ACCESS.2020.2969780.
[11] Seok Jun Bu and Hae Jung Kim. Optimized URL Feature Selection Based on Genetic Algorithm Embedded Deep Learning for Phishing Website Detection. Electronics. 2022. 10.3390/electronics11071090.
[12] Anjaneya Awasthi and Noopur Goel. Phishing Website Prediction Using Base and Ensemble Classifier Techniques with Cross Validation. Cybersecurity. 2022. 10.1186/s42400-022-00126-9.
[13] Nguyet Quang Do and Ali Selamat and Ondrej Krejcar and Takeru Yokoi. Phishing Webpage Classification via Deep Learning Based Algorithms An Empirical Study. Applied Sciences. 2021. 10.3390/app11199210.
[14] Asif Ejaz and Adnan Noor Mian and Sanaullah Manzoor. Life Long Phishing Attack Detection Using Continual Learning. Scientific Reports. 2023. 10.1038/s41598-023-37552-9.
[15] Norah Alsuqayh and Areej Alhogail and Abdulrahman Mirza. Hybrid Feature Selection with SHAP Based Explainable AI for Interpretable Phishing Website Detection. Journal of King Saud University Computer and Information Sciences. 2026. 10.1007/s44443-026-01281-6.
[16] Hoc Minh Le and Van Thuong Nguyen. A Secure and Explainable Phishing Detection Framework Using Deep Learning and LLM Based Reasoning. Discover Informatics. 2026. 10.1007/s44564-026-00020-3.
[17] Asadullah Safi and Satwinder Singh. A Systematic Literature Review on Phishing Website Detection Techniques. Journal of King Saud University Computer and Information Sciences. 2023. 10.1016/j.jksuci.2023.01.004.
[18] A Suryan and C Kumar and M Mehta and R Juneja and A Sinha. Learning Model for Phishing Website Detection. EAI Endorsed Transactions on Scalable Information Systems. 2020. 10.4108/eai.13-7-2018.163804.
[19] Paulius Vaitkevicius and Virginijus Marcinkevicius. Comparison of Classification Algorithms for Detection of Phishing Websites. Informatica. 2020. 10.15388/20-INFOR404.
[20] Abdullah Al Alyan and Saad Al Ahmadi. Robust URL Phishing Detection Based on Deep Learning. KSII Transactions on Internet and Information Systems. 2020. 10.3837/tiis.2020.07.001.
[21] Igino Corona and Battista Biggio and Matteo Contini and Luca Piras and Roberto Corda and Mauro Mereu and Guido Mureddu and Davide Ariu and Fabio Roli. DeltaPhish Detecting Phishing Webpages in Compromised Websites. Computer Security ESORICS 2017. 2017. 10.1007/978-3-319-66402-6_22.
[22] Ali Aljofey and Qingshan Jiang and Abdur Rasool and Hui Chen and Wenyin Liu and Qiang Qu and Yang Wang. An Effective Detection Approach for Phishing Websites Using URL and HTML Features. Scientific Reports. 2022. 10.1038/s41598-022-10841-5.
[23] Erzhou Zhu and Yuyang Chen and Chengcheng Ye and Xuejun Li and Feng Liu. OFS NN An Effective Phishing Websites Detection Model Based on Optimal Feature Selection and Neural Network. IEEE Access. 2019. 10.1109/ACCESS.2019.2920655.
[24] Mohamed Abdelkarim Remmide and Boumahdi Fatima and Narhimene Boustia and Chalabia Lilia Feknous and Romaissa Della. Detection of Phishing URLs Using Temporal Convolutional Network. Procedia Computer Science. 2022. 10.1016/j.procs.2022.10.209.
[25] Haifeng Jiang and Yu Chen and Yingjie Zhu and Xin Xu and Yuejia Song and Qiwei Chen. D PhishNet A Dual Branch Network for URL and HTML Feature Fusion in Phishing Webpage Detection. Computer Networks. 2025. 10.1016/j.comnet.2025.111648.
[26] Catherine Olivia Winanda and Andreas Liujaya Wiranata and Azani Cempaka Sari. Phishing Website Detection Using a Stacking Ensemble Classifier of Random Forest LightGBM and CatBoost. Procedia Computer Science. 2026. 10.1016/j.procs.2026.08.222.
[27] Abdellah Rezoug and Mohamed Bader el den. A Robust Ensemble Learning Approach to URL Based Phishing Webpage Detection. Big Data and Cognitive Computing. 2026. 10.3390/bdcc10050136.
[28] Scott M Lundberg and Su In Lee. A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems 30. 2017. https://proceedings.neurips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html.
[29] Chuan Guo and Geoff Pleiss and Yu Sun and Kilian Q Weinberger. On Calibration of Modern Neural Networks. Proceedings of Machine Learning Research 70. 2017. https://proceedings.mlr.press/v70/guo17a.html.
[30] Battista Biggio and Igino Corona and Davide Maiorca and Blaine Nelson and Nedim Srndic and Pavel Laskov and Giorgio Giacinto and Fabio Roli. Evasion Attacks against Machine Learning at Test Time. ECML PKDD 2013. 2013. https://hdl.handle.net/11584/105260.
[31] M. K. Bagwani, A. Gangwar, K. Vishwakarma and V. K. Tiwari, “Real-time signature-based detection and prevention of DDOS attacks in cloud environments,” International Journal of Science and Research Archive, vol 12, no 2, pp 2929–2935, 2024, doi: 10.30574/ijsra.2024.12.2.1608. Source
[32] A. Khare, N. Choudhary and M. K. Bagwani, “Trustworthy and Adaptive Intrusion Detection for Imbalanced IoT Traffic,” International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, vol 1, no 1, pp 80–86, 2026, doi: 10.68307/k9pxqe13. Source
33] P. G. K. S. Mahesh Kumar Bagwani, "Performance comparison of REST API and GraphQL in a micro services architecture," International Conference on Data Science, Artificial Intelligence and Advanced Computing, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mr.Dhyanendra Patel, Mr. Prakash Kumar Maravi, Mr. Kamlesh Raghuwanshi, Dr. Surabhi Karsoliya
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies (IJAICET) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Under this license, users are free to share, copy, redistribute, adapt, and build upon the published material for any purpose, including commercial use, provided appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Authors retain copyright of their work while granting IJAICET the right to publish, archive, distribute, and index the article. The journal supports the free exchange of scientific knowledge through open access publishing and encourages the widest possible dissemination of research.
