Enhancing Network Resilience: A Deep Neural Network Approach to Automated Intrusion Detection
International Journal of Advanced Research in Science Communication and Technology · 01.07.2026 · 570
DOI: 10.48175/ijarsct-36879 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 01.07.2026. Verfasst von Mrs.Prajakta N. Sakhare. Die Arbeit nennt 8 Literaturangaben.
Abstract (Originalsprache)
Traditional, rule-based Intrusion Detection Systems (IDS) are no longer sufficient to combat the sheer volume and diversity of contemporary network attacks due to the quick development of cyber-adversary capabilities. Autonomous systems with high-speed pattern recognition are desperately needed as perimeter defenses deal with more complex "low-and-slow" exploits and zero-day vulnerabilities. This study introduces a cutting-edge Intrusion Detection System (IDS) that uses Deep Neural Networks (DNN) to recognize and categorize malicious network traffic with the least amount of human involvement. The suggested approach extracts high-level historical characteristics from unprocessed network packets using a multi-layered Feedforward Neural Network architecture. Our DNN method successfully captures the non-linear correlations found in complex datasets like the CIC-IDS2017, in contrast to shallow machine learning models. The approach uses sophisticated preprocessing methods, like as dimensionality reduction and feature normalization, to manage the high-velocity data streams common in business settings. According to experimental assessments, the DNN-based model detects minority-class attacks like User-to-Root (U2R) and Remote-to-Local (R2L) vulnerabilities far more effectively than conventional Support Vector Machines (SVM) and Decision Trees. This study shows that deep learning offers a scalable, future-proof solution for real-time threat mitigation by attaining exceptional accuracy and a surprisingly low false-alarm rate. According to the research, incorporating DNNs into security operations centers can strengthen the defense-in-depth posture of contemporary digital infrastructures and significantly shorten response times.
Zitieren
APA
Sakhare, M. N. (2026). Enhancing Network Resilience: A Deep Neural Network Approach to Automated Intrusion Detection. International Journal of Advanced Research in Science Communication and Technology, 570. https://doi.org/10.48175/ijarsct-36879
Vancouver
Sakhare MN. Enhancing Network Resilience: A Deep Neural Network Approach to Automated Intrusion Detection. International Journal of Advanced Research in Science Communication and Technology. 2026:570. doi:10.48175/ijarsct-36879
BibTeX
@article{Sakhare2026,
author = {Sakhare, Mrs.Prajakta N.},
title = {Enhancing Network Resilience: A Deep Neural Network Approach to Automated Intrusion Detection},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {570},
doi = {10.48175/ijarsct-36879}
}
EUVIMED