AI-Driven Cybersecurity Threat Detection: A Hybrid ML–DL Framework for Real-Time Network Intrusion Detection

Author(s)	Mr. Sandeep Singh, Ms. Anshu Dhabhai, Ms. Dimple Jain, Ms. Khushboo Sharma
Country	India
Abstract	This paper presents a hybrid AI framework combining classical machine learning (ML), deep learning (DL), and unsupervised anomaly detection to improve detection of network intrusions and emerging cyber threats. We review recent literature on AI applications in cybersecurity, describe representative datasets used for evaluation (CIC-IDS2017, UNSW-NB15, NSL-KDD), propose a modular architecture (data collection → preprocessing → feature engineering → ensemble models → decision fusion), and discuss implementation choices, evaluation metrics, expected results, limitations (data imbalance, adversarial examples, interpretability), and future directions.
Keywords	AI, machine learning, deep learning, intrusion detection system (IDS), anomaly detection, ensemble, CIC-IDS2017, UNSW-NB15, NSL-KDD.
Field	Computer > Network / Security
Published In	Volume 6, Issue 6, November-December 2025
Published On	2025-12-03
DOI	https://doi.org/10.63363/aijfr.2025.v06i06.2284
Short DOI	https://doi.org/hbdssj

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research