Brand Design Data Security and Privacy Protection Under 6G Network Slicing Architecture

International Journal of Network Management, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 27, 2025

ABSTRACT The rapid growth of networking technology has generated several situations and issues in the field safeguarding critical brand design data present hyper connected context, particularly with arrival 6 th Generation (6G). As development relies more on cloud‐based services, protecting client intellectual property (IP) is essential. By using 6G network slicing architecture, which contains dedicated, secure sections for improved encryption, anomaly detection systems, research suggested a solution to such issues. includes features as performance, security measurements, user privacy measures. methodology entails pre‐processing Z‐score normalization standardize feature distributions, followed by Principal Component Analysis (PCA) decrease dimensions. proposed method uses Fully Homomorphic Encryption Driven Quantum Support Vector Machine (FHE‐QSVM) detect anomalies real time while assuring safe efficient resource allocation dedicated slices. FHE‐QSVM model produced significant metrics, accuracy (98%), recall (96%), precision (97%), F1‐score (96%) accurately categorizing threats maintaining confidentiality. finding shows enhances both Overall, this strategy offers scalable AI‐powered highlighting importance creative real‐time monitoring, meet contemporary standards.

Language: Английский

Design and Implementation of Intelligent Digital Media Interaction System Based on 6G Network Slicing

International Journal of Network Management, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 27, 2025

ABSTRACT Rapid growth in intelligent digital media interaction systems (IDMIS) has created new difficulties controlling and optimizing content distribution engagement, especially with the impending 6G networks. The purpose of investigate is to create an system that uses network slicing increase communication user experience through seamless connectivity, dynamic distribution, real‐time engagement. structure includes a dynamic, multilayered architecture for IDMIS, capital allocated based on demand type. machine learning (ML) algorithms predict behavior optimize delivery real time. To correctly behavior, research gathers data capture users' performance preference (historical data, demographics, contextual feedback). Once collected, are processed reduce dimensionality using principal component analysis (PCA). Refined Support Vector Machine Integrated Flying Fox Optimization (RSVM‐FFO) predicts optimizes Metrics used evaluate RSVM‐FFO approach, such as F1‐score (98.12%), accuracy (98.59%), precision (98.57%), recall (98.17%). results reveal suggested considerably improve effectiveness by reducing latency bandwidth usage while providing highly responsive experience. Finally, advancement high‐performance, customized services combination IDMIS slicing.

Language: Английский