A Cost-Sensitive Machine Learning Framework for Zero-Day Phishing Detection Under Class Imbalance and Cross-Dataset Distribution Shifts
Keywords:
Phishing Detection, Machine Learning, Zero-Day Phishing, Cost-Sensitive Learning, Class Imbalance, Distribution Shift, Cybersecurity.Abstract
Phishing is one of the most harmful types of cyber-attacks because of the frequent changes made by the criminals in URLs and webpage structures. In this paper, the focus is made on the development of a framework for detecting zero-day phishing using cost-sensitive learning considering the issues of class imbalance and cross-dataset distribution shifts. For the assessment of the Logistic Regression, Support Vector Machine, Random Forest, and XGBoost methods, the metrics of precision, recall, F1-score, and balanced accuracy are used. In this framework, the costs for false negatives are increased, and the cross-dataset testing is performed. It was discovered that XGBoost is able to detect the threat efficiently, and the use of cost-sensitive learning increases the recall rate.
References
Abdelnaby, K. M. (2026). A Systematic Multi-Paradigm Evaluation Framework for Network Intrusion Detection in Fog-IoT Environments: Deep Learning, Transformer, and Ensemble Methods Across Deployment Tiers. Symmetry, 18(9), 1438.
Al Siam, A., Faruqui, N., Azad, A., & Moni, M. A. (2026). Securing the Unseen: A Comprehensive Exploration Review of AI‐Powered Models for Zero‐Day Attack Detection. Expert Systems, 43(3), e70217.
AlJuhaiman, H. A., Emad-ul-Haq, Q., Kim, K., & Lee, S. (2026). Automated Cyber Threat Intelligence Extraction from Distributed Honeypots: A Hybrid Machine Learning Approach. Electronics, 15(13), 2900.
Alrabaia, Z., & Taseen, M. (2025). How Consistent Are Different ML Algorithms in Detecting Phishing URLs: Testing Simple Machine Learning Methods on Different Sets of Phishing URLs.
Alsunaidi, S. J., Aljamaan, H., & Hammoudeh, M. (2025). Leveraging machine learning models to improve smart contract security: A survey of vulnerabilities and detection methods. ACM Computing Surveys, 58(6), 1-37.
Bindra, V. (2026). CADENCE-Ran: A Calibrated, Drift-Aware, Explainable Framework for Early Open-Set Ransomware Detection Under Enterprise Label Delays.
Biyouki, A., Lotfipour, S., & Haghi, B. (2025). An enhanced deep learning framework for intrusion classification enterprise network using multi-branch CNN-attention architecture. Scientific Reports, 16(1), 3962.
Devi, R. R., Raja, J. E., & Chin, Y. B. (2025). Reinforcement learning with graph neural network (RL-GNN) fusion for real-time financial fraud detection: a context-aware community mining approach. Scientific Reports, 15(1), 42953.
Ding, J., Shen, Z., & Liu, W. (2026). Game-theoretic cost-sensitive adversarial training for robust cloud intrusion detection against GAN-based evasion attacks. Applied Sciences, 16(8), 3944.
Gurappa, S., Hariprasad, Y., Iyengar, S. S., & Chaudhary, N. K. (2026). Botnet detection on CTU-13 using lightweight machine learning models. arXiv preprint arXiv:2605.23004.
Jodayree, M., Ghafi, A. K., Amiri, S., & Shaykholeslami, P. (2026). Explainable zero-day attack detection in IoMT using transformer-based time-series modeling. Scientific Reports.
Morshedi, R., & Matinkhah, S. M. (2025). A comprehensive review of deep learning techniques for anomaly detection in iot networks: Methods, challenges, and datasets. Engineering Reports, 7(9), e70415.
Redhu, A., Ranganath, S., Rajdeo, M., Agarwal, D., Subramani, R., Nashine, S. P., ... & Srinivasan, K. (2026). AI-powered malware intelligence: a review of machine and deep learning paradigms in detection and classification. Artificial Intelligence Review.
Yasin, M., Akter, S., Khan, M. A. N., Tasnim, M., Sultana, S., Jakir, T., ... & Akter, K. S. (2026). XAI-Enabled Intelligent Detection and Mitigation of Zero-Day Attacks in Healthcare IoT. International Journal of Future Innovative Science and Technology (IJFIST), 9(5), 1807.
Zenia, M. M. (2025). Impact of Deep Learning on Real-Time Network Intrusion Detection: A Quantitative Evaluation Using Benchmark Datasets. Review of Applied Science and Technology, 4(04), 296-338.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
