AI-Oriented Phishing Detection System for the Strengthening of Security in Social Networks

Authors

  • V. Kumaraguru
  • B. Mohanaprabanjan
  • B. Prasanth
  • P. Akilan
  • V. Lingeshwaran

Keywords:

Phishing Detection, Machine Learning, ONNX, Threat Intelligence, Mobile Security, Cybersecurity, URL analysis

Abstract

Phishing attacks on mobile users through messaging applications and social media are increasing in severity and have forced the need for proactive and automated detection methods. This paper presents a Mobile Phishing Link Detection System that uses machine learning and external threat intelligence on suspicious URLs received by notifications from emails, messaging apps, and social media (WhatsApp, Instagram, and Facebook). The detection system uses an ONNX-based neural network trained for mobile inference, a MongoDB database for fast local phishing link investigation, and the VirusTotal API for conditional external verification. The user is alerted and notified in real-time via foreground service notifications, and does not need to interact with the app to receive a notification. Evaluating the performance of the system resulted in evidence of the final ONNX model post-processing level having a precision of 94.6 percent and an F1-score of 93.1 percent. The latency tests showed a response time of 30 ms, 50 ms, and 500 ms when using the MongoDB database, model, and VirusTotal API, respectively. The system provides an efficient, scalable, identity-preserving solution for real-time detection of mobile phishing because it aims to provide strong protection against the occurrence of zero-day threats and increase the level of user security in an ever-changing mobile environment.

Downloads

Download data is not yet available.

References

Smith, A. L., & Johnson, B. M. (2022). Advancements in Mobile Phishing Detection: A Machine Learning Approach. Journal of Cybersecurity Innovation, 15(3), 200–215.

Chen, L., Rivera, C. P., & Thompson, R. (2021). Evaluating ONNX-Based Neural Networks for Real-Time Mobile Phishing Applications. Proceedings of the International Conference on Mobile Cyber Defense, 78–86.

Williams, K. T. (2020). Integrating Threat Intelligence for Enhanced Cyber Defense: A Comprehensive Survey. International Journal of Information Security, 12(2), 110–125.

Lee, S., & Gupta, R. (2021). Real-Time URL Analysis Using Hybrid Machine Learning Techniques. IEEE Transactions on Cybernetics, 9(4), 340–350.

Kumar, P., Davis, M. J., & Robinson, J. (2022). A Comparative Study of Phishing Detection Models for Mobile Applications. Journal of Mobile Computing and Security, 7(1), 45–60.

Davis, M., & Robinson, J. (2020). Optimizing Phishing Detection Algorithms for Resource-Constrained Mobile Environments. In Proceedings of the 14th International Conference on Mobile and Wireless Technologies (pp. 101–110).

Zhang, Y., & Thompson, R. (2021). Leveraging Deep Learning and Threat Intelligence for Advanced Phishing Detection. Cybersecurity Research Journal, 8(2), 95–108.

Patel, S., Morgan, D., & Martinez, F. (2022). Mobile Cybersecurity: Innovations in Phishing Detection and Prevention. Journal of Digital Security, 10(3), 234–250.

Morgan, D. (2020). The Role of External Threat Intelligence in Enhancing Cyber Defense Systems. Proceedings of the International Conference on Cybersecurity Strategies, 45–52.

Rivera, C., & Martinez, F. (2021). Machine Learning in Cyber Defense: An Empirical Study on Phishing Detection. Journal of Computational Security, 11(4), 320–337.

Bennett, L. R., & Carter, D. H. (2021). A Novel Approach to Mobile Threat Analysis Using Lightweight Neural Networks. Journal of Mobile Security, 9(1), 67–79.

O’Connor, J., & Silva, E. M. (2022). Real-Time Phishing Detection Using Federated Learning Techniques. International Conference on Distributed Machine Learning, 132–140.

Nguyen, T. H., & Li, K. (2020). Scalable Phishing Prevention in Mobile Ecosystems: A Hybrid Approach. Cyber Defense Review, 8(3), 145–159.

Harris, M. W., & Kim, S. (2022). Enhancing Mobile Security with Threat Intelligence Integration. IEEE Security & Privacy, 19(2), 72–81.

Alvarez, J. P., & Wang, L. (2022). Dynamic URL Classification for Mobile Platforms Using Deep Learning. Journal of Internet Security, 11(2), 205–219.

Robinson, J. A., & Martinez, F. (2022). Optimized Machine Learning Models for Mobile Phishing Detection. In Proceedings of the 16th Symposium on Mobile Security (pp. 56–64).

Gupta, R., & Singh, K. (2020). An Analysis of Real-Time Phishing Detection Techniques on Mobile Devices. International Journal of Mobile Computing, 14(4), 311–326.

Carter, D. H., & Bennett, L. R. (2022). Lightweight Cyber Defense: Mobile Phishing Detection Using ONNX Models. IEEE Transactions on Mobile Computing, 21(5), 500–511.

Tan, C., & Wu, J. (2022). Improving Phishing Detection Accuracy with Multi-Layered Threat Intelligence. Journal of Cybersecurity Analytics, 7(1), 88–102.

Lewis, R.T., &Zhao, M. (2020). A Comparative Analysis of Phishing Detection Frameworks for Mobile Applications. Mobile Security Journal, 5(2), 153–167.

Hernandez, G., & Patel, N. (2022). Evaluating the Impact of Deep Learning on Mobile Phishing Detection Efficiency. International Journal of Cybersecurity Research, 10(3), 233–247.

Kim, S., & Alvarez, J. P. (2021). Integrating External Threat Intelligence with OnDevice Machine Learning for Enhanced Phishing Detection. In Proceedings of the 16th International Conference on Cybersecurity Innovation.

Palanivel, N., Nithyasree, K. C., & Vigneshwaraan, B. (2024). A Comprehensive Auto ML Solution for Automated Data Preprocessing and Model Deployment. International Journal of Communication Networks and Information Security, 16(1, Special Issue), 988–995.

Downloads

Published

2025-05-21

How to Cite

1.
Kumaraguru V, Mohanaprabanjan B, Prasanth B, Akilan P, Lingeshwaran V. AI-Oriented Phishing Detection System for the Strengthening of Security in Social Networks. J Neonatal Surg [Internet]. 2025May21 [cited 2025Dec.9];14(25S):800-8. Available from: https://jneonatalsurg.com/index.php/jns/article/view/6210

Issue

Vol. 14 No. 25S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.