Autors: Stoilova, G. O., Ilieva, R. I.
Title: AI-Enhanced Cybersecurity Models for E-Commerce: Strategic Defense Through Intelligent Systems
Keywords: ai-driven defense, anomaly detection, artificial intelligence, cybersecurity, deep learning, digital forensics, e-commerce, IDS/IPS, threat modeling, zero trust

Abstract: The rapid digitization of commerce introduces unprecedented security challenges due to increasingly complex threat vectors. This paper revisits the cybersecurity landscape in e-commerce and repositions the discourse in light of emerging artificial intelligence techniques. We propose a shift from reactive to predictive, intelligent cyber defense, incorporating AI-based models for threat detection, behavioral analytics, and dynamic response. By integrating supervised learning, unsupervised anomaly detection, and reinforcement learning agents into the cybersecurity framework, e-businesses can fortify their infrastructures with adaptability and resilience. The study presents an evolved threat-defense matrix supported by diagrams and an AI-enhanced security model for future-proof e-commerce.

References

  1. Ali, M., Qaisar, S., & Farooq, Q. U. (2023). A comprehensive survey on AI for cybersecurity: Challenges and opportunities. IEEE Access, 11, 67032–67056. https://doi.org/10.1109/ACCESS.2023.3260490
  2. Apple Inc. (2021). Machine learning research. https://machinelearning.apple.com/
  3. Ghosh, S., Ghosh, P., & Chatterjee, S. (2022). Zero trust security in AI-driven digital environments: Emerging patterns and architectures. Computers & Security, 114, 102608. https://doi.org/10.1016/j.cose.2021.102608
  4. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
  5. Microsoft. (2022). Zero Trust Architecture with AI-driven security automation. https://www.microsoft.com/security/blog
  6. Moustafa, N., Slay, J., & Creech, G. (2017). Big data analytics for intrusion detection systems: A survey. Journal of Big Data, 4(1), 1–22. https://doi.org/10.1186/s40537-017-0070-0
  7. Nguyen, T. T., & Redmond, S. J. (2021). Reinforcement learning for cybersecurity: A review of applications and challenges. ACM Computing Surveys (CSUR), 54(7), 1–36. https://doi.org/10.1145/3453160
  8. PayPal. (2023). How machine learning protects online transactions. https://newsroom.paypal-corp.com
  9. Sarker, I. H. (2020). Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-020-00392-2
  10. Sommer, R., & Paxson, V. (2010). Outside the closed world: On using machine learning for network intrusion detection. IEEE Symposium on Security and Privacy, 305–316. https://doi.org/10.1109/SP.2010.25
  11. Splunk Inc. (2021). UEBA with unsupervised machine learning. https://www.splunk.com/
  12. Tounsi, W., & Rais, H. (2018). A survey on cybersecurity threat intelligence. Computers & Security, 72, 212–233. https://doi.org/10.1016/j.cose.2017.09.001
  13. Ullah, I., & Mahmoud, Q. H. (2021). A hybrid model for efficient intrusion detection using machine learning algorithms. Journal of Network and Computer Applications, 179, 102980. https://doi.org/10.1016/j.jnca.2021.102980
  14. Zhang, Y., Liu, J., Jiang, C., Wang, Y., & Sun, X. (2019). Anomaly detection in smart e-commerce environments using LSTM networks. Journal of Ambient Intelligence and Humanized Computing, 10(12), 4861–4873. https://doi.org/10.1007/s12652-018-1091-z

Issue

2025 34th International Scientific Conference Electronics, ET 2025 - Proceedings, pp. 1-7, 2025, Bulgaria, https://doi.org/10.1109/ET66806.2025.11204166

Copyright IEEE Xplore

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus