EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep Feature-Driven TAO Tree Fusion Model for Autonomous Intrusion Detection in Software-Defined 6G Network Slicing Architectures

B. L. N. Swamy, G. Udaykiran Bhargava, G. Raviraju, V. Ravindra Naik

American Journal of AI Cyber Computing Management · 31.05.2026 · 6 (2) · 874-887

DOI: 10.64751/ajaccm.v6i2.577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of AI Cyber Computing Management, online erschienen am 31.05.2026. Verfasst von B. L. N. Swamy und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The evolution of 6G networks introduces significant demands for secure, adaptive, and high-performance communication systems. Conventional network monitoring and intrusion detection approaches, largely based on static rules and manual inspection, are insufficient for managing the complexity and scale of modern network environments. These methods often fail to detect advanced cyber threats and are ineffective in optimizing network performance under dynamic conditions. This research proposes a Machine Learning (ML)-driven framework based on Classification and Regression Tree (CART) principles for dual-purpose analysis, including attack classification and throughput prediction. The system integrates multiple ML techniques, such as Support Vector Machine (SVM), k-Nearest Neighbors (KNN), and a custom-designed Tree-based Adaptive Optimization (TAO) and an enhanced hybrid Deep Convolutional Neural Network (CNN) with TAO-CART (Deep CNN-TAO CART) architecture. The Deep CNN module performs automated feature extraction, while the TAO-CART ensemble improves classification and regression performance for complex network traffic patterns. These models are trained to accurately identify malicious traffic patterns while simultaneously predicting network throughput. To improve model performance, preprocessing techniques including Label Encoding, feature scaling through Standardization, and class balancing using Synthetic Minority Over-sampling Technique (SMOTE) are applied. This integrated approach enhances generalization capability and robustness across diverse network scenarios. Experimental results indicate that the Deep CNN – TAO CART ensemble model achieves superior classification accuracy along with reliable regression performance compared to individual models. Furthermore, the system is implemented through a web-based interface using the Flask framework, enabling real-time analysis and user interaction. The proposed solution provides a scalable and intelligent framework for improving network security and optimizing performance in next-generation communication systems.

Zitieren

APA

Swamy, B. L. N., Bhargava, G. U., Raviraju, G., & Naik, V. R. (2026). Deep Feature-Driven TAO Tree Fusion Model for Autonomous Intrusion Detection in Software-Defined 6G Network Slicing Architectures. American Journal of AI Cyber Computing Management, 6(2), 874-887. https://doi.org/10.64751/ajaccm.v6i2.577

Vancouver

Swamy BLN, Bhargava GU, Raviraju G, Naik VR. Deep Feature-Driven TAO Tree Fusion Model for Autonomous Intrusion Detection in Software-Defined 6G Network Slicing Architectures. American Journal of AI Cyber Computing Management. 2026;6(2):874-887. doi:10.64751/ajaccm.v6i2.577

BibTeX
@article{Swamy2026,
  author = {Swamy, B. L. N. and Bhargava, G. Udaykiran and Raviraju, G. and Naik, V. Ravindra},
  title = {Deep Feature-Driven TAO Tree Fusion Model for Autonomous Intrusion Detection in Software-Defined 6G Network Slicing Architectures},
  journal = {American Journal of AI Cyber Computing Management},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {874--887},
  doi = {10.64751/ajaccm.v6i2.577}
}
Kostenlos starten →