Certificate: View Certificate
Published Paper PDF: PDF
Confirmation Letter: View
DOI: https://doi.org/10.63345/ijrmeet.org.v9.i10.1
Pavan Reddy Vaka
Faculty of Computer Applications & Information Science
North East Christian University
Dimapur, Nagaland
Dr. Seema Sharma
Faculty of Computer Applications & Information Science
North East Christian University
Dimapur, Nagaland
Abstract
Cyber defence has undergone a paradigm shift over the past three decades, transitioning from perimeter-focused protection to intelligent, adaptive, and predictive security architectures. The rapid expansion of digital ecosystems—cloud computing, IoT, 5G, virtualized networks, and edge systems—has intensified the scale and complexity of cyber threats. Traditional security mechanisms, though foundational, struggle to address the speed, stealth, and sophistication of modern cyberattacks. Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), offers transformative capacities for enhancing detection, response, prediction, and automated defence. This research paper examines the evolutionary trajectory of cyber defence, evaluates limitations of legacy systems, and explores how AI-enabled architectures improve threat intelligence, intrusion detection, anomaly detection, malware analysis, autonomous response, and resilience. The paper concludes by identifying future directions, such as explainable security, adversarially robust AI, cognitive security ecosystems, and fully autonomous cyber operations.
References
[1] I. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” Proc. ICLR, 2015.
[2] M. Ring, D. Landes, M. Marinov, and A. Hotho, “Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study,” IEEE Access, vol. 8, pp. 104463–104473, 2020.
[3] Canadian Institute for Cybersecurity, “CICIDS2017 dataset,” Univ. of New Brunswick, 2017.
[4] W. Wang, M. Zhu, X. Zeng, X. Ye, and Y. Sheng, “Malware traffic classification using convolutional neural networks,” IEEE Int. Conf. Computer Communication and Networks, 2017.
[5] S. Naseer, Y. Saleem, S. Khalid et al., “Enhanced network anomaly detection using deep neural networks,” IEEE Access, vol. 6, pp. 48231–48246, 2018.
[6] T. Kim, B. Kang, M. Rho, S. Sezer, and E. Gyu, “Long short-term memory recurrent neural network classifier for intrusion detection,” ICIS 2016, pp. 1–6.
[7] N. Moustafa and J. Slay, “UNSW-NB15: A comprehensive dataset for network intrusion detection systems,” MilCIS Conference, IEEE, 2015.
[8] J. Apruzzese, M. Colajanni, L. Ferretti, A. Guido, and M. Marchetti, “On the effectiveness of machine and deep learning for cyber security,” IEEE Trans. Dependable Secure Comput., vol. 18, no. 2, pp. 935–951, 2021.
[9] A. Abeshu and N. Chilamkurti, “Deep learning models for cyber security in IoT networks,” IEEE Trans. Smart Grid, vol. 9, no. 4, pp. 2410–2420, 2018.
[10] A. Javaid, Q. Niyaz, W. Sun, and M. Alam, “A deep learning approach for network intrusion detection using NSL-KDD dataset,” Proc. 9th EAI Int. Conf. Bio-Inspired Information and Communications, 2016.
[11] S. Bhosale and A. Pawar, “AI-based SIEM enhancements using UEBA,” Proc. 2021 IEEE Intl. Conf. Innovations in Information Embedded and Communication Systems (ICIIECS), 2021.
[12] NIST, “Zero Trust Architecture (NIST SP 800-207),” National Institute of Standards and Technology, 2020.
[13] E. Papadogiannakis, S. Ioannidis, and E. Markatos, “Anomaly detection in encrypted traffic: Machine learning for next-gen firewalls,” ACM FOCI Workshop, 2020.
