Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200158,
        author = {Gemini Ashokkumar Parmar and Dr. Tosal M. Bhalodia},
        title = {Strengthening Data Privacy and Security in Modern Healthcare Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4010-4014},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200158},
        abstract = {Network intrusion detection is a critical security task for identifying malicious activity in computer networks. Traditional machine learning methods often rely on static classification, while reinforcement learning can adaptively learn decision policies from interaction data. This paper presents a Deep Q-Network (DQN)-based intrusion detection system that classifies network traffic into normal and attack categories using the NSL-KDD dataset. The proposed framework applies one-hot encoding, standardization, experience replay, and an epsilon-greedy strategy to train an intelligent agent for binary classification. Experimental results show that the proposed model achieves an accuracy of 80.02%, precision of 92.92%, and recall of 70.35%. The results indicate that reinforcement learning can be effectively adapted for intrusion detection and can provide strong precision in identifying attack traffic.},
        keywords = {Attack Classification, Deep Reinforcement Learning, DQN, Intrusion Detection System, Network Security, NSL-KDD},
        month = {June},
        }