A hybrid machine learning and explainable AI framework for optimizing risk-based authentication
Clinical Snapshot
PICO Framework
| P — Population | Online platform users requiring authentication |
| I — Intervention | Hybrid machine learning framework combining ensemble classifiers, fuzzy logic, clustering, and optimization for risk-based authentication |
| C — Comparator | Traditional authentication methods or baseline risk assessment approaches |
| O — Outcomes | Authentication accuracy, precision, recall, F1-score, equal error rate (EER), and authentication decision optimization |
Bottom Line
This study presents a sophisticated hybrid machine learning framework for risk-based authentication that demonstrates impressive performance metrics on large datasets. While the technical approach is comprehensive, combining ensemble methods, fuzzy logic, and explainable AI, the study lacks crucial methodological details and statistical rigor. The absence of confidence intervals, significance testing, and comparison with existing methods limits confidence in the findings. For healthcare applications, the framework could potentially enhance security for electronic health records and patient data systems, particularly relevant given Australia's digital health initiatives. However, implementation would require substantial technical infrastructure and careful validation in real-world healthcare environments. The high reported accuracy and low error rates are promising, but independent validation and cost-effectiveness analysis are needed before widespread adoption. Healthcare organizations should await peer-reviewed validation studies and consider pilot implementations with robust monitoring before full deployment.
Key Findings
P Value: Not reported
Effect Size: High discrimination with 99.41% precision and 98.04% recall
Primary Outcome: Authentication framework performance with 97.77% accuracy
Nnt Or Sensitivity: Equal Error Rate (EER) of 0.0303 indicating excellent discrimination capability
Confidence Interval: Not reported
Clinical Application
Requires significant computational infrastructure and technical expertise for implementation Relevant for Australian Digital Health Agency initiatives and compliance with Privacy Act 1988 and Notifiable Data Breaches scheme Healthcare organizations requiring secure authentication for electronic health records and patient data systems
Abstract
As online platforms continue to grow, the need for strong authentication mechanisms becomes increasingly important to protect sensitive information and networks. Risk-Based Authentication (RBA) is an adaptive approach that dynamically adjusts authentication decisions based on user behavior and contextual information, thereby improving both security and user experience. This study proposes a hybrid RBA framework that integrates machine learning ensemble techniques, fuzzy logic, clustering, and optimization to enhance account takeover detection and dynamic risk assessment. The ensemble classifier, combining Gradient Boosting, SVM, and XGBoost, predicts the probability of account compromise based on login behavior, device attributes, and network information. K-Means clustering is used to generate initial risk thresholds (low, medium, and high), which are further refined using a fuzzy logic system to map probabilities to risk levels. The L-BFGS-B optimization algorithm is employed to fine-tune fuzzy membership boundaries and improve threshold consistency. Experimental results demonstrate strong performance, achieving 97.77% accuracy, 99.41% precision, 98.04% recall, 98.72% F1-score, and an EER of 0.0303. On large-scale datasets ranging from 2M to 30M records, the proposed framework demonstrates consistent improvement in authentication decisions. For the 2M dataset, Allow Login actions increase from 349,432-349,923, while Deny Login actions decrease from 1,462-1,228, along with a slight reduction in additional authentication prompts. Furthermore, the use of Explainable AI techniques, particularly SHAP, enhances the transparency and interpretability of the model, supporting more informed decision-making. Overall, the proposed framework is accurate, adaptive, and suitable for real-world risk-based authentication applications.
References
- 1.Sasikumar, K., & Nagarajan, S. (2026). A hybrid machine learning and explainable AI framework for optimizing risk-based authentication. PLoS One. https://doi.org/10.1371/journal.pone.0349095
Related Research
Journal of medical Internet research
Advancing Human-Centered AI in Clinical Decision Support: Sociocognitive Human-in-the-Loop Study in HIV Care
2 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Neural networks : the official journal of the International Neural Network Society
MFBD: Model-free backdoor defense based on vision-language pre-trained models
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service