Sunil Bajeja
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sunil Bajeja has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Enoch Success Boakai
Marwadi University
2 shared publications Abhinav Pathak
School of Technology Management and Engineering, NMIMS, Indore, India
1 shared publication- Chinnem Rama Mohan
Narayana Engineering College
1 shared publication - Divyakant Meva
Marwadi University
1 shared publication - Hetal M. Bhatt
Marwadi University
1 shared publication - Kalpesh Popat
Marwadi University, Rajkot, India
1 shared publication
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 36-45
Review of Artificial Intelligence Techniques for Ransomware Classification
- 2 July 2026
- Published by Springer Nature
- p. 36-45
Review of Artificial Intelligence Techniques for Ransomware Classification
- 29 November 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S168-S175
Deep learning on genomic sequences for rapid identification of drug-resistant tuberculosis
- 29 November 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S168-S175
Deep learning on genomic sequences for rapid identification of drug-resistant tuberculosis
- 6 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Standards Magazine
- Vol. PP (24712825) , 1-8
Comparative Evaluation of Machine Learning Models for Phishing Website Detection Using URL-Based Features
Phishing remains one of the most pervasive cybersecurity threats, exploiting human trust and deceptive website design to steal sensitive credentials. Traditional defense mechanisms, such as blacklists and heuristic rules, often fail to detect zero-day and evolving phishing attacks. This study presents a comparative analysis of machine learning algorithms for phishing detection based on URL-level features using the UCI Phishing Websites Dataset, which contains 11,055 instances and 30 predictive attributes. Five classifiers, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) were implemented and rigorously evaluated on statistical measures. Experimental results indicate that Random Forest and SVM achieve superior performance, with their predictive capability further enhanced through hyperparameter tuning. These findings not only highlight the effectiveness of ensemble methods and kernel-based classifiers in phishing detection but also provide valuable insights into the discriminative power of specific URL-based features. The outcomes of this work contribute to developing robust, interpretable, and data-driven approaches for proactive phishing mitigation.
- 6 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Standards Magazine
- Vol. PP (24712825) , 1-8
Comparative Evaluation of Machine Learning Models for Phishing Website Detection Using URL-Based Features
Phishing remains one of the most pervasive cybersecurity threats, exploiting human trust and deceptive website design to steal sensitive credentials. Traditional defense mechanisms, such as blacklists and heuristic rules, often fail to detect zero-day and evolving phishing attacks. This study presents a comparative analysis of machine learning algorithms for phishing detection based on URL-level features using the UCI Phishing Websites Dataset, which contains 11,055 instances and 30 predictive attributes. Five classifiers, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) were implemented and rigorously evaluated on statistical measures. Experimental results indicate that Random Forest and SVM achieve superior performance, with their predictive capability further enhanced through hyperparameter tuning. These findings not only highlight the effectiveness of ensemble methods and kernel-based classifiers in phishing detection but also provide valuable insights into the discriminative power of specific URL-based features. The outcomes of this work contribute to developing robust, interpretable, and data-driven approaches for proactive phishing mitigation.
- 4 November 2025
- Published by Springer Nature
- p. 194-206
Title: Advances, Challenges, and Future Directions of Deep Convolutional Neural Networks in Medical Imaging: A Systematic Review
- 4 November 2025
- Published by Springer Nature
- p. 194-206
Title: Advances, Challenges, and Future Directions of Deep Convolutional Neural Networks in Medical Imaging: A Systematic Review
- 31 October 2025
- Published by Springer Nature
- p. 488-498
The Role of Indo-Israeli Cyber Cooperation in Countering Cyber Threats
- 31 October 2025
- Published by Springer Nature
- p. 488-498
The Role of Indo-Israeli Cyber Cooperation in Countering Cyber Threats
- Open Access
- 30 August 2025
- Published by Springer Nature
- p. C1
Correction to: Artificial Intelligence Based Smart and Secured Applications
- 30 August 2025
- Published by Springer Nature
- p. C1
Open AccessCorrection to: Artificial Intelligence Based Smart and Secured Applications
- 12 August 2025
- Published by Springer Nature
- p. 435-450
Proactive Approaches to IoT Network Security: A Review of Threats and Strategic Amelioration Techniques
- 12 August 2025
- Published by Springer Nature
- p. 435-450
Proactive Approaches to IoT Network Security: A Review of Threats and Strategic Amelioration Techniques
- 16 June 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-12
Enhancing Cloud-Native Relational Database Systems: Proposed Design Patterns for AWS RDS Application
- 16 June 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-12
Enhancing Cloud-Native Relational Database Systems: Proposed Design Patterns for AWS RDS Application
- 2 May 2024
- Published by Springer Nature
- p. 141-162
A Survey of Machine Learning Techniques in Phishing Detection
- 2 May 2024
- Published by Springer Nature
- p. 141-162
A Survey of Machine Learning Techniques in Phishing Detection