1 MS in Computer Science and Engineering, East West University, Dhaka, Bangladesh.
2 BSc in CSE, Dhaka International University.
3 CSE, Leading University.
4 M.Sc , Ph. D in Mechanical Engineering, Xi'an Jiaotong University, China.
5 CSE, Daffodil International University.
International Journal of Science and Research Archive, 2025, 17(01), 1084-1092
Article DOI: 10.30574/ijsra.2025.17.1.2928
Received on 20 September 2025; revised on 26 October 2025; accepted on 29 October 2025
This paper explores the development of adaptive threat detection systems in cybersecurity by leveraging deep learning techniques. It investigates the integration of AI-driven models capable of dynamically identifying and responding to evolving cyber threats with enhanced accuracy and speed. Emphasizing the challenges posed by complex, rapidly changing attack patterns, this study evaluates advanced neural architectures and model interpretability to build robust, real-time detection frameworks. The findings demonstrate significant potential for deep learning to transform cybersecurity defenses through continuous adaptation and intelligent threat assessment.
Adaptive threat detection; Deep learning cybersecurity; AI-driven security systems; Real-time cyber threat identification; Neural network threat detection; Explainable AI in cybersecurity
Preview Article PDF
EFAZ KABIR, Md Nyem Hasan Bhuiyan, Samya Datta, Mandal Shubhankar and Mohammad Quayes Bin Habib. AI-Driven Cybersecurity: Building Adaptive Threat Detection Systems Using Deep Learning. International Journal of Science and Research Archive, 2025, 17(01), 1084-1092. Article DOI: https://doi.org/10.30574/ijsra.2025.17.1.2928.
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
